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

    Neuronpedia

    INDEX
    Explanations

    long texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transformer
    -0.06
    _perms
    -0.06
     malt
    -0.06
     duel
    -0.06
    oks
    -0.06
     folding
    -0.06
    radan
    -0.06
     metam
    -0.06
    .Exception
    -0.06
    zano
    -0.06
    POSITIVE LOGITS
     explaining
    0.07
    bers
    0.06
    -eslint
    0.06
     JFrame
    0.06
    छ
    0.06
    lectron
    0.06
    CARD
    0.06
    sk
    0.06
     clen
    0.06
    .enum
    0.06
    Act Density 0.064%

    No Known Activations