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

    Neuronpedia

    INDEX
    Explanations

    Scientific/Medical texts

    np_max-act · gemini-2.0-flash

    The neuron is a detector for nominalized words—especially agent‐ or action‐nouns ending in suffixes like “-ator” or “-ation.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /pp
    -0.06
    (candidate
    -0.06
    YLE
    -0.06
     Zd
    -0.06
    nowledge
    -0.06
     frustrations
    -0.06
     Nath
    -0.06
    yle
    -0.06
     knob
    -0.06
     specific
    -0.06
    POSITIVE LOGITS
    몰
    0.07
    인
    0.06
     Minnesota
    0.06
    plemented
    0.06
    _ACTIONS
    0.06
    scious
    0.06
    .Bool
    0.06
    float
    0.06
     جلسه
    0.06
     cosmic
    0.06
    Act Density 0.555%

    No Known Activations