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

    Neuronpedia

    INDEX
    Explanations

    rereading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    наў
    0.67
    deps
    0.66
     haz
    0.65
     স্বচ্ছ
    0.65
    maxn
    0.64
    শ্র
    0.63
    筋肉
    0.62
    кульп
    0.61
     சொல்க
    0.61
    작가
    0.61
    POSITIVE LOGITS
     Income
    0.74
    緘
    0.72
     Metabolic
    0.72
     Fellow
    0.70
     ചെയ്യുന്ന
    0.70
     Campus
    0.69
     Farms
    0.68
     cession
    0.68
    ociety
    0.68
    GetAsyncKeyState
    0.67
    Act Density 0.002%

    No Known Activations