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
     FStar
    -0.07
     Ses
    -0.07
    เก
    -0.06
     Celt
    -0.06
    uat
    -0.06
    YPD
    -0.06
    ιθ
    -0.06
    丘
    -0.06
     고개를
    -0.06
    Рµ
    -0.06
    POSITIVE LOGITS
     promotions
    0.07
     completed
    0.07
     experimented
    0.06
     proportional
    0.06
    ··
    0.06
    测试
    0.06
     InvalidOperationException
    0.06
    324
    0.06
     yelled
    0.06
    characters
    0.06
    Act Density 0.007%

    No Known Activations