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

    Neuronpedia

    INDEX
    Explanations

    prime number check

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setId
    0.40
     engage
    0.38
    engage
    0.37
    entryId
    0.37
     Engage
    0.36
     conversaciones
    0.36
    חס
    0.36
    ⁸
    0.36
    ⁶
    0.35
    centering
    0.35
    POSITIVE LOGITS
    绡
    0.43
     lesqu
    0.41
     zwei
    0.41
     двух
    0.40
     dvou
    0.40
     ander
    0.39
     fichier
    0.39
     ২
    0.38
     ജില്ലാ
    0.38
    foregroundView
    0.38
    Act Density 0.006%

    No Known Activations