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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    herits
    -0.06
     Počet
    -0.06
     David
    -0.06
     Ov
    -0.06
     codes
    -0.06
     đá
    -0.06
    _null
    -0.06
    .by
    -0.06
    illustr
    -0.06
     junit
    -0.06
    POSITIVE LOGITS
     Sanct
    0.07
    ै↵
    0.07
    ‌پدی
    0.06
    .graph
    0.06
     ар
    0.06
     فرود
    0.06
     Giuliani
    0.06
     CommonModule
    0.06
     dancing
    0.06
     sph
    0.06
    Act Density 0.002%

    No Known Activations