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

    Neuronpedia

    INDEX
    Explanations

    Amsterdam Dam Square history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ın
    0.52
     טי
    0.51
    Eau
    0.49
     ምክ
    0.49
     เรียน
    0.48
     事業
    0.46
    are
    0.46
     הא
    0.46
    te
    0.45
    Њ
    0.45
    POSITIVE LOGITS
    最低
    0.46
    ython
    0.43
     чого
    0.42
    ций
    0.40
     হুগলীর
    0.40
     prescribe
    0.39
     athleticism
    0.39
    心情
    0.39
     expliquer
    0.39
    yil
    0.39
    Act Density 0.002%

    No Known Activations