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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _AD
    -0.07
     doit
    -0.07
     SAM
    -0.06
     안
    -0.06
     covariance
    -0.06
    enes
    -0.06
    rays
    -0.06
     Về
    -0.06
     setters
    -0.06
     submissions
    -0.06
    POSITIVE LOGITS
     removeObject
    0.06
     dateFormatter
    0.06
    lá
    0.06
    ultureInfo
    0.06
    فاع
    0.06
     doomed
    0.06
     dildo
    0.06
    _VECTOR
    0.06
     meticulously
    0.06
     организа
    0.06
    Act Density 0.003%

    No Known Activations