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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     we've
    -0.07
    Namespace
    -0.07
    Damage
    -0.07
    quick
    -0.07
     sums
    -0.07
    itut
    -0.07
    warts
    -0.07
    spec
    -0.07
     innocence
    -0.07
     pearl
    -0.07
    POSITIVE LOGITS
    规律
    0.13
     ежедневно
    0.10
     consistently
    0.10
     evenings
    0.10
     amén
    0.09
     incline
    0.09
    每天
    0.09
     hábito
    0.09
     सुनिश्चित
    0.09
     નિયમ
    0.09
    Act Density 0.008%

    No Known Activations