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

    Neuronpedia

    INDEX
    Explanations

    pass through code or law

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     takže
    0.83
     inflater
    0.72
     பாரன்ஹீ
    0.71
    йом
    0.70
    intelligence
    0.70
    alon
    0.70
    賺
    0.69
    ১৪
    0.69
     movimento
    0.69
    >`
    0.67
    POSITIVE LOGITS
     살펴
    0.76
     azonban
    0.74
     Atty
    0.72
     الحق
    0.71
     Careful
    0.69
    hauses
    0.66
    ujourd
    0.65
     però
    0.65
     änd
    0.65
    تم
    0.65
    Act Density 0.002%

    No Known Activations