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

    Neuronpedia

    INDEX
    Explanations

    code and identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fiber
    -0.06
     Crest
    -0.06
    面议
    -0.06
    qx
    -0.06
     Nunes
    -0.06
    다는
    -0.06
     ﾄ
    -0.06
    October
    -0.06
    .FLAG
    -0.06
     knih
    -0.06
    POSITIVE LOGITS
    _ang
    0.07
    452
    0.06
    .drag
    0.06
    _Main
    0.06
     $\
    0.06
    iasm
    0.06
    .visualization
    0.06
    AO
    0.06
     yolu
    0.06
     triệu
    0.06
    Act Density 0.038%

    No Known Activations