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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables like x

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ihe
    0.93
    T
    0.87
     সব
    0.86
     pues
    0.83
     เจ้า
    0.82
    которые
    0.81
     SGD
    0.80
     gdy
    0.79
    绩
    0.79
     manteniendo
    0.79
    POSITIVE LOGITS
    cknowled
    1.10
    ের
    0.88
    ₁
    0.88
    ে
    0.86
    ν
    0.85
    ̂
    0.83
    0.81
    erdapat
    0.81
    specialchars
    0.81
    ною
    0.80
    Act Density 0.430%

    No Known Activations