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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    かった
    -0.08
    NOTE
    -0.06
    что
    -0.06
     GAR
    -0.06
    .footer
    -0.06
    .Patient
    -0.06
    basename
    -0.06
    'R
    -0.06
     railways
    -0.06
     mois
    -0.06
    POSITIVE LOGITS
     Ordering
    0.07
     Со
    0.07
     conferred
    0.06
     pretending
    0.06
    -pattern
    0.06
     troubles
    0.06
     Unsupported
    0.06
    ứng
    0.06
    .vel
    0.06
    aña
    0.06
    Act Density 0.125%

    No Known Activations