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

    Neuronpedia

    INDEX
    Explanations

    learning rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     totals
    0.89
    totals
    0.84
     scorecard
    0.80
    measured
    0.77
     totales
    0.76
    Measurements
    0.76
     counted
    0.74
    receipt
    0.73
     measurements
    0.73
    measurable
    0.71
    POSITIVE LOGITS
     Radius
    1.06
    半径
    1.04
    Radius
    1.02
    radius
    1.01
     radius
    1.00
     damping
    0.97
    damping
    0.95
     hyperparameters
    0.95
     sensitivity
    0.93
     设置
    0.92
    Act Density 0.849%

    No Known Activations