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

    Neuronpedia

    INDEX
    Explanations

    fitting regression models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    कर्ता
    0.41
     günd
    0.41
    fillText
    0.41
    akarta
    0.40
    염
    0.40
     opiniones
    0.40
    fach
    0.39
    行动
    0.39
     priorit
    0.38
     czynności
    0.38
    POSITIVE LOGITS
     fitted
    1.57
     fitting
    1.53
     regression
    1.42
     fit
    1.39
     Fitting
    1.34
    fitted
    1.32
    Fitting
    1.31
     Regression
    1.30
    fitting
    1.30
    Regression
    1.30
    Act Density 0.032%

    No Known Activations