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

    Neuronpedia

    INDEX
    Explanations

    /libs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cavalry
    -0.07
     supplement
    -0.07
     NSStringFromClass
    -0.07
     Paolo
    -0.07
    .Layer
    -0.06
     xAxis
    -0.06
     you
    -0.06
    所以说
    -0.06
    辐
    -0.06
     maid
    -0.06
    POSITIVE LOGITS
    文化艺术
    0.08
    ERICAN
    0.07
    بريط
    0.07
    理想信念
    0.07
    óg
    0.07
    readcr
    0.07
    ניסי
    0.07
    STE
    0.07
     ciné
    0.07
    实干
    0.07
    Act Density 0.000%

    No Known Activations