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

    Neuronpedia

    INDEX
    Explanations

    information, documentation, or effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тах
    0.45
     permitted
    0.43
     ยัง
    0.42
     corrective
    0.42
     saham
    0.42
     осо
    0.41
    tted
    0.41
     car
    0.41
     Scand
    0.41
     frayed
    0.41
    POSITIVE LOGITS
    К
    0.63
    Werk
    0.60
    あ
    0.55
    Questo
    0.55
    现在
    0.54
    Now
    0.54
    С
    0.53
    We
    0.52
    Depuis
    0.52
    إن
    0.52
    Act Density 0.001%

    No Known Activations