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

    Neuronpedia

    INDEX
    Explanations

    probation and parish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.45
    ta
    1.12
    ti
    1.08
    z
    0.98
    ↵
    0.96
    h
    0.96
     I
    0.95
    si
    0.95
    tu
    0.94
    ty
    0.90
    POSITIVE LOGITS
    ي
    1.20
    ̀ng
    0.98
    iquement
    0.80
    كو
    0.79
    合物
    0.78
     capaces
    0.78
    ার
    0.76
    的服务
    0.75
    ية
    0.75
    كان
    0.74
    Act Density 0.004%

    No Known Activations