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

    Neuronpedia

    INDEX
    Explanations

    identifying words followed by others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ।
    0.55
    noch
    0.46
    Umb
    0.43
    '
    0.43
     that
    0.43
     Males
    0.42
    cks
    0.42
    最后
    0.41
     দশ
    0.41
    rast
    0.41
    POSITIVE LOGITS
    ანა
    0.50
    やる
    0.48
    様々な
    0.46
    ಳ
    0.46
     või
    0.45
    امہ
    0.45
    ایر
    0.45
     다양한
    0.45
    ತನ
    0.45
    メソッド
    0.45
    Act Density 0.000%

    No Known Activations