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

    Neuronpedia

    INDEX
    Explanations

    android, manifest, content, app, os

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ය
    0.84
    ISIONS
    0.84
    erent
    0.83
    साठी
    0.82
    arati
    0.81
    eria
    0.79
    sion
    0.79
     нарушения
    0.78
    วาม
    0.77
    lendi
    0.77
    POSITIVE LOGITS
    TE
    0.82
    CON
    0.78
    hi
    0.76
    in
    0.75
    PL
    0.74
    int
    0.73
    Set
    0.73
    Find
    0.73
    ang
    0.71
    do
    0.71
    Act Density 0.001%

    No Known Activations