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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.92
    个
    0.86
    ushing
    0.75
     and
    0.73
    *
    0.73
    드
    0.72
    "))
    0.72
    /
    0.70
    ane
    0.69
    ("
    0.68
    POSITIVE LOGITS
    arán
    0.93
    го
    0.92
    can
    0.85
    。
    0.84
     semblables
    0.81
    ார்
    0.80
    ાર
    0.80
    ни
    0.80
    ку
    0.79
     operativos
    0.78
    Act Density 0.033%

    No Known Activations