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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    選擇
    -0.08
    泽
    -0.08
    失控
    -0.08
    ход
    -0.07
    obbled
    -0.07
    תה
    -0.07
    aims
    -0.07
    加之
    -0.07
    cho
    -0.07
    璞
    -0.07
    POSITIVE LOGITS
     الكمبي
    0.08
    Fashion
    0.07
     manufacturers
    0.07
     noises
    0.07
     presentation
    0.07
     economists
    0.07
     printed
    0.07
    rases
    0.07
    .ToolStripButton
    0.06
     cinema
    0.06
    Act Density 0.001%

    No Known Activations