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

    Neuronpedia

    INDEX
    Explanations

    percentage of cars are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ไม่
    1.66
    و
    1.59
    '
    1.34
    יי
    1.13
    ണ്ട്
    1.13
    م
    1.10
    ’
    1.09
    ל
    1.09
    يد
    1.08
    ו
    1.08
    POSITIVE LOGITS
    ство
    1.50
    蟆
    1.20
     n
    1.14
    หนด
    1.13
    طة
    1.12
    સ
    1.11
    age
    1.09
    up
    1.08
    ことがあります
    1.08
     nogen
    1.08
    Act Density 0.735%

    No Known Activations