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

    Neuronpedia

    INDEX
    Explanations

    numbers, digits, and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cream
    1.15
    Cont
    1.07
    vidas
    1.03
    Cap
    0.98
    Buffer
    0.97
    Poly
    0.97
    Heat
    0.96
    Collection
    0.95
    Nature
    0.95
    Sh
    0.95
    POSITIVE LOGITS
     diar
    1.01
    姶
    0.95
    ্দ্র
    0.93
     naa
    0.93
     harem
    0.92
     halve
    0.92
     cyanide
    0.91
     hunde
    0.91
     phrases
    0.90
     incest
    0.90
    Act Density 0.080%

    No Known Activations