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

    Neuronpedia

    INDEX
    Explanations

    code/data plots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prazo
    -0.09
     draagt
    -0.09
     prison
    -0.08
     повреж
    -0.08
     करेगा
    -0.08
     Cologne
    -0.08
     ചെയ്യും
    -0.08
     prisoners
    -0.08
     Hund
    -0.08
     trägt
    -0.08
    POSITIVE LOGITS
     plotted
    0.13
     vary
    0.12
    Plot
    0.10
     subplot
    0.10
     trends
    0.10
     plot
    0.10
    走势
    0.09
     ylabel
    0.09
     trend
    0.09
     Plot
    0.09
    Act Density 0.014%

    No Known Activations