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

    Neuronpedia

    INDEX
    Explanations

    strategic choices, principles, performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sqrt
    0.38
     lagi
    0.37
     запас
    0.37
     consape
    0.37
     atmospheric
    0.36
    oze
    0.36
     svom
    0.36
    godic
    0.35
     زمین
    0.35
     agam
    0.35
    POSITIVE LOGITS
     Hedge
    0.44
    adolid
    0.39
    ❿
    0.39
     Brisbane
    0.38
     Dickens
    0.38
     Ballon
    0.38
    مرين
    0.38
    ಕ್ಷ
    0.38
     eccentricity
    0.37
     Gallows
    0.37
    Act Density 0.000%

    No Known Activations