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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pow
    -0.07
     Films
    -0.07
    ρκ
    -0.07
    Football
    -0.06
    夫人
    -0.06
    _VIS
    -0.06
    ‌ک
    -0.06
    WebKit
    -0.06
     nhớ
    -0.06
     ترك
    -0.06
    POSITIVE LOGITS
    elog
    0.07
    El
    0.06
    ΟΓ
    0.06
     rim
    0.06
     culmination
    0.06
     Tub
    0.06
    >V
    0.06
    -el
    0.06
    уб
    0.06
    iasm
    0.06
    Act Density 0.089%

    No Known Activations