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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     захи
    0.46
    <unused626>
    0.46
     pernikahan
    0.45
     武田
    0.44
    秏
    0.43
     היה
    0.43
    <unused2046>
    0.43
    伌
    0.42
     состояния
    0.41
    ਤ
    0.41
    POSITIVE LOGITS
     allocate
    0.50
    class
    0.48
    F
    0.47
    s
    0.47
    '}).
    0.46
     Err
    0.45
     cypress
    0.45
     strict
    0.45
    "#
    0.44
    alloc
    0.44
    Act Density 0.000%

    No Known Activations