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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    зу
    -0.06
    .INPUT
    -0.06
     amigos
    -0.06
     bolest
    -0.06
    社会
    -0.06
    胶
    -0.06
     režim
    -0.06
     oportun
    -0.06
    _drv
    -0.06
     trolling
    -0.06
    POSITIVE LOGITS
     tradi
    0.09
     preval
    0.06
     speci
    0.06
    .TRAILING
    0.06
    nerRadius
    0.06
     substitute
    0.06
     revised
    0.06
     Gradient
    0.06
     Quy
    0.06
     чор
    0.06
    Act Density 0.154%

    No Known Activations