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

    Neuronpedia

    INDEX
    Explanations

    Alfred

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RICT
    -0.08
    صات
    -0.07
    ्रमण
    -0.07
    .condition
    -0.07
     Coal
    -0.07
    inyin
    -0.06
    iến
    -0.06
     compress
    -0.06
    .notification
    -0.06
     ratios
    -0.06
    POSITIVE LOGITS
    {\
    0.07
     kế
    0.07
     Volk
    0.06
     impoverished
    0.06
     bước
    0.06
     assure
    0.06
    ेयर
    0.06
    21
    0.06
    ❤
    0.06
    孝
    0.06
    Act Density 0.003%

    No Known Activations