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

    Neuronpedia

    INDEX
    Explanations

    offend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     upp
    -0.07
    ประก
    -0.07
     sorts
    -0.06
    isper
    -0.06
     руч
    -0.06
     buurt
    -0.06
    .OrderByDescending
    -0.06
     biraz
    -0.06
    ServiceProvider
    -0.06
    Prefs
    -0.06
    POSITIVE LOGITS
    _PRIVATE
    0.07
    ék
    0.06
    Bar
    0.06
     alan
    0.06
     accompanied
    0.06
    .stdin
    0.06
     Bene
    0.06
     WT
    0.06
    ulaire
    0.06
    basket
    0.06
    Act Density 0.034%

    No Known Activations