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

    Neuronpedia

    INDEX
    Explanations

    Questions/conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coins
    -0.07
    伯
    -0.07
    translations
    -0.07
    (rect
    -0.06
    ASCII
    -0.06
     myst
    -0.06
    .RemoveAll
    -0.06
     доб
    -0.06
    털
    -0.06
    deploy
    -0.06
    POSITIVE LOGITS
     pediatric
    0.07
     Clayton
    0.06
     mimic
    0.06
    modal
    0.06
     sánh
    0.06
    each
    0.06
     máximo
    0.06
     mandated
    0.06
    -modal
    0.06
     pimp
    0.06
    Act Density 0.128%

    No Known Activations