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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     внут
    -0.07
    ूट
    -0.07
     Hits
    -0.07
    (channel
    -0.07
    ์ท
    -0.07
    !("
    -0.06
     ptr
    -0.06
    เล
    -0.06
     مناس
    -0.06
    스코
    -0.06
    POSITIVE LOGITS
     Norm
    0.07
    $order
    0.06
    {-
    0.06
    -an
    0.06
    chapter
    0.06
     disciplinary
    0.06
     physically
    0.06
     bounding
    0.06
    [][
    0.06
     turkey
    0.06
    Act Density 0.003%

    No Known Activations