Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    w

    np_max-act · gemini-2.0-flash

    names of historical figures and locations related to ancient civilizations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on 1–2 letter sequences (and occasional full names like “iron”) that match chemical‐element symbols (Cr, W, Al, Ar, Fe, Pu, Co, V, Zn, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Arrival
    -0.08
     CFL
    -0.07
     missions
    -0.07
     Horn
    -0.07
     Shell
    -0.07
    다가
    -0.07
    utherland
    -0.07
     Kent
    -0.06
     Dreams
    -0.06
    navigation
    -0.06
    POSITIVE LOGITS
    ;/
    0.06
    azor
    0.06
    //************************************************************************
    0.06
    	main
    0.06
     آی
    0.06
    ':'
    0.06
    _leave
    0.06
    FORE
    0.06
    structor
    0.06
     ἐ
    0.06
    Act Density 0.161%

    No Known Activations