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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ModelAdmin
    -0.69
     ویکی‌پدیای
    -0.65
    تقاوى
    -0.65
    脚注の使い方
    -0.56
    Rhestr
    -0.56
     handleMessage
    -0.56
    DoubleQuotes
    -0.54
     الحره
    -0.54
    tonsoft
    -0.54
    rrggbb
    -0.54
    POSITIVE LOGITS
     
    0.76
    )$
    0.43
    tenth
    0.43
    ub
    0.42
     six
    0.42
    else
    0.42
     ).
    0.41
    ()))
    0.41
    ).
    0.41
    ())));
    0.41
    Act Density 0.002%

    No Known Activations