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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cost
    -0.07
    cmd
    -0.07
     Hour
    -0.07
    JUST
    -0.07
     Gross
    -0.06
    (guild
    -0.06
    ádu
    -0.06
     biological
    -0.06
     pork
    -0.06
     McDon
    -0.06
    POSITIVE LOGITS
     départ
    0.07
     віт
    0.07
    .setCellValue
    0.06
    ılacak
    0.06
     FILE
    0.06
     각
    0.06
    ارت
    0.06
     among
    0.06
    _FIRST
    0.06
    UED
    0.06
    Act Density 0.000%

    No Known Activations