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

    Neuronpedia

    INDEX
    Explanations

    precision measurements and calibration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    威胁
    0.54
     नारेबाजी
    0.53
    名单
    0.53
     اداکار
    0.53
     pourrez
    0.52
     मार्केट
    0.52
    تاة
    0.52
    语气
    0.51
     inciting
    0.51
    soundcloud
    0.51
    POSITIVE LOGITS
     calibration
    1.06
     accuracy
    1.01
     Calibration
    0.93
     accuracies
    0.92
     measurements
    0.91
     accurate
    0.90
     calibrated
    0.90
     precision
    0.89
     calibrate
    0.89
     measurement
    0.89
    Act Density 0.100%

    No Known Activations