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

    Neuronpedia

    INDEX
    Explanations

    ibration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adies
    -0.08
     unary
    -0.07
    श
    -0.07
    ंड
    -0.07
     Friedman
    -0.07
     dominance
    -0.06
    หนอง
    -0.06
    anoia
    -0.06
     ποι
    -0.06
     Mutex
    -0.06
    POSITIVE LOGITS
     calibration
    0.13
     Calibration
    0.13
     calibrated
    0.10
    _calibration
    0.08
    <br
    0.08
     gr
    0.07
    bar
    0.07
    ibr
    0.07
    _per
    0.07
     caliber
    0.07
    Act Density 0.002%

    No Known Activations