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

    Neuronpedia

    INDEX
    Explanations

    android permissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    1.02
    .
    0.88
     are
    0.85
    ما
    0.84
    да
    0.79
     to
    0.77
    ها
    0.77
    AN
    0.76
    URE
    0.75
     a
    0.75
    POSITIVE LOGITS
    ే
    0.71
    rün
    0.63
     eléctricas
    0.63
     해당하는
    0.63
     constants
    0.59
     пе
    0.59
    ↵↵↵
    0.59
    ᱐
    0.59
     귀
    0.58
     пом
    0.58
    Act Density 0.001%

    No Known Activations