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

    Neuronpedia

    INDEX
    Explanations

    graphical plots and trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Brows
    0.37
    暖かい
    0.36
    成了
    0.35
     каран
    0.34
    န
    0.34
     ফেল
    0.34
    aginaw
    0.33
     INSTALL
    0.33
    +"','"+
    0.33
     നേടി
    0.33
    POSITIVE LOGITS
     slope
    1.16
     plotted
    1.07
     Slope
    1.04
    曲线
    1.03
     slopes
    1.02
     curve
    1.00
    slope
    1.00
     plotting
    0.96
     curves
    0.96
     axes
    0.93
    Act Density 0.133%

    No Known Activations