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

    Neuronpedia

    INDEX
    Explanations

    strings/code

    np_max-act · gemini-2.0-flash

    This neuron never responds to any tokens (all activations are zero).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pBuffer
    -0.07
    _MULT
    -0.07
    _CHARSET
    -0.06
     шах
    -0.06
    .relative
    -0.06
    .scrollHeight
    -0.06
    -short
    -0.06
     пак
    -0.06
     fuer
    -0.06
    haft
    -0.06
    POSITIVE LOGITS
    .There
    0.07
    ##
    0.07
     Median
    0.07
    ATORS
    0.07
    __))
    0.07
     ancestor
    0.07
    }/#{
    0.07
     Wishlist
    0.06
     THERE
    0.06
    There
    0.06
    Act Density 0.002%

    No Known Activations