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

    Neuronpedia

    INDEX
    Explanations

    respect

    np_max-act · gemini-2.0-flash

    The neuron fires on multi‐digit numerical tokens—especially years or dates.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    อย
    -0.07
    _Key
    -0.07
     об
    -0.07
    .translate
    -0.07
    Perfect
    -0.06
    /connect
    -0.06
    map
    -0.06
     taps
    -0.06
     tourist
    -0.06
     meat
    -0.06
    POSITIVE LOGITS
     esteemed
    0.08
     respected
    0.08
    拜
    0.07
     reputation
    0.06
    上が
    0.06
     revered
    0.06
     lsp
    0.06
     Establishment
    0.06
     USC
    0.06
     ↑
    0.06
    Act Density 0.018%

    No Known Activations