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

    Neuronpedia

    INDEX
    Explanations

    183

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    970
    -0.07
     испыт
    -0.07
    272
    -0.07
    466
    -0.07
    dra
    -0.07
    uble
    -0.07
    cos
    -0.06
     thử
    -0.06
    ~
    -0.06
     кров
    -0.06
    POSITIVE LOGITS
    (new
    0.07
     noun
    0.07
     Benton
    0.07
    .InteropServices
    0.07
     MessageBoxButtons
    0.07
    :maj
    0.07
    (client
    0.07
     자신의
    0.07
     Bishop
    0.07
    .autoconfigure
    0.07
    Act Density 0.010%

    No Known Activations