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

    Neuronpedia

    INDEX
    Explanations

    python import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.92
    L
    0.89
    I
    0.89
    ן
    0.83
    P
    0.78
    ي
    0.77
    i
    0.77
    V
    0.77
    IO
    0.75
    J
    0.75
    POSITIVE LOGITS
     a
    0.67
     insignificant
    0.64
     crystal
    0.61
     sandwiched
    0.60
     recuperar
    0.58
    ியும்
    0.58
     scammers
    0.57
    鬯
    0.57
    ש
    0.55
    ଢ
    0.55
    Act Density 0.003%

    No Known Activations