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

    Neuronpedia

    INDEX
    Explanations

    code and text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fashion
    -0.06
     "./
    -0.06
     intake
    -0.06
    “Well
    -0.06
    "Well
    -0.06
    Snake
    -0.06
     saber
    -0.06
     pursuing
    -0.06
    (console
    -0.06
    adalafil
    -0.06
    POSITIVE LOGITS
    CM
    0.06
    ikers
    0.06
    Sac
    0.06
    twig
    0.06
     soğ
    0.06
    ويك
    0.06
    рії
    0.06
    ाफ
    0.06
    /sys
    0.06
    .Team
    0.06
    Act Density 0.054%

    No Known Activations