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

    Neuronpedia

    INDEX
    Explanations

    numbers, units, and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bola
    0.86
    Liter
    0.77
     ſh
    0.76
    喎
    0.75
    정을
    0.75
    שה
    0.75
    Kamu
    0.74
    Jwt
    0.73
    商品
    0.73
    Ҳ
    0.73
    POSITIVE LOGITS
     strawberry
    0.79
     vanes
    0.75
     vane
    0.70
     Nascimento
    0.70
     caballero
    0.68
    িত্ব
    0.68
     flora
    0.67
     Vereins
    0.66
     eigenvalues
    0.66
     perdido
    0.65
    Act Density 0.001%

    No Known Activations