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

    Neuronpedia

    INDEX
    Explanations

    Regression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dormant
    -0.09
    	packet
    -0.09
     पुष
    -0.09
     antise
    -0.08
    勇
    -0.08
     persecut
    -0.08
    rej
    -0.08
     Doyle
    -0.08
     fé
    -0.08
    Appear
    -0.08
    POSITIVE LOGITS
    Regression
    0.11
     regression
    0.10
     predicting
    0.10
     forecasting
    0.10
     Regression
    0.10
     mse
    0.09
    .predict
    0.09
    预测
    0.09
    _scalar
    0.09
     آموزش
    0.09
    Act Density 0.010%

    No Known Activations