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

    Neuronpedia

    INDEX
    Explanations

    measurement units conversion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بینی
    0.72
     predicts
    0.71
    Predict
    0.71
     çat
    0.69
    iftung
    0.67
    ubb
    0.65
    udukan
    0.64
     اجتماع
    0.64
     triggered
    0.63
    predict
    0.61
    POSITIVE LOGITS
     units
    2.08
     Units
    1.96
    Units
    1.92
     conversion
    1.90
     UNITS
    1.83
     conversions
    1.83
    units
    1.74
    Conversion
    1.73
     unit
    1.71
    conversion
    1.69
    Act Density 0.346%

    No Known Activations