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

    Neuronpedia

    INDEX
    Explanations

    user

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hog
    -0.07
     Bison
    -0.07
    級
    -0.07
    Shoot
    -0.07
    ๋
    -0.07
    宋代
    -0.06
    MAN
    -0.06
    ฤษ
    -0.06
    峘
    -0.06
    .GetCurrentMethod
    -0.06
    POSITIVE LOGITS
     philanth
    0.08
     zal
    0.07
    .setLayoutParams
    0.07
     talents
    0.07
     bande
    0.06
     spoiler
    0.06
    틈
    0.06
    んです
    0.06
     следует
    0.06
     gmail
    0.06
    Act Density 0.071%

    No Known Activations