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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eylül
    -0.07
     Apprent
    -0.07
    шиб
    -0.07
    -Oct
    -0.07
     Dispatcher
    -0.07
     샤
    -0.06
    üs
    -0.06
    https
    -0.06
    _PIX
    -0.06
     Newfoundland
    -0.06
    POSITIVE LOGITS
     divers
    0.06
     ousted
    0.06
    Jamie
    0.06
     amp
    0.06
    ＾
    0.06
     Roosevelt
    0.06
     Pointer
    0.06
    =set
    0.06
     eig
    0.06
    @Setter
    0.06
    Act Density 0.014%

    No Known Activations