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

    Neuronpedia

    INDEX
    Explanations

    major strategic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     よう
    1.17
    ಕ್ತಿ
    1.12
    즈
    1.09
    сказа
    1.07
     stipend
    1.07
     tür
    1.06
    ਧ
    1.06
    स्तिष्क
    1.05
    әне
    1.03
    サム
    1.02
    POSITIVE LOGITS
    ל
    1.32
    م
    1.18
    喃
    1.09
    Ĕ
    1.08
    கு
    1.08
    erode
    1.05
    دار
    1.04
    под
    1.03
    platforms
    1.03
    Celebrate
    1.03
    Act Density 0.001%

    No Known Activations