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

    Neuronpedia

    INDEX
    Explanations

    film names and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ヤ
    0.38
    ધ
    0.36
     शार्
    0.35
    鋈
    0.35
    ミラ
    0.34
     Sanford
    0.34
    setPassword
    0.34
    痂
    0.34
    吵
    0.33
     cetera
    0.33
    POSITIVE LOGITS
     Aaron
    0.45
     Film
    0.45
     film
    0.44
    Film
    0.43
     अरुण
    0.43
    film
    0.43
     Blüten
    0.43
    Aurora
    0.43
     Aron
    0.42
     Aro
    0.41
    Act Density 0.001%

    No Known Activations