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

    Neuronpedia

    INDEX
    Explanations

    Ensuring accuracy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    冀
    -0.07
    _adc
    -0.07
    productId
    -0.07
    Rand
    -0.07
     prevState
    -0.07
    &p
    -0.07
    Pdf
    -0.07
     baff
    -0.07
     aer
    -0.07
    入职
    -0.06
    POSITIVE LOGITS
    활동
    0.07
     włas
    0.07
     Guaranteed
    0.07
    夜
    0.07
    商店
    0.06
     kim
    0.06
    rove
    0.06
     במרכז
    0.06
    \Cache
    0.06
     gündem
    0.06
    Act Density 0.089%

    No Known Activations