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

    Neuronpedia

    INDEX
    Explanations

    avoiding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     subscription
    -0.07
    ybrid
    -0.07
     entrada
    -0.07
     incorrectly
    -0.06
     paralle
    -0.06
     verifies
    -0.06
     duro
    -0.06
    러운
    -0.06
     склада
    -0.06
     judged
    -0.06
    POSITIVE LOGITS
     cous
    0.07
     avoiding
    0.06
     lessen
    0.06
    阳
    0.06
    aced
    0.06
    .archive
    0.06
     Tud
    0.06
     tud
    0.06
    ouncements
    0.06
     Tân
    0.06
    Act Density 0.059%

    No Known Activations