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

    Neuronpedia

    INDEX
    Explanations

    safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    وة
    -0.07
     trat
    -0.06
    图
    -0.06
     联
    -0.06
    立刻
    -0.06
    Maint
    -0.06
    ‌شود
    -0.06
     Goods
    -0.06
    -за
    -0.06
     都
    -0.06
    POSITIVE LOGITS
    .driver
    0.07
     Nikol
    0.07
    flt
    0.06
     GLint
    0.06
     temas
    0.06
    .frequency
    0.06
    ophilia
    0.06
    ッシュ
    0.06
     گفته
    0.06
    (scale
    0.06
    Act Density 0.007%

    No Known Activations