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

    Neuronpedia

    INDEX
    Explanations

    ulin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swore
    -0.07
    /Game
    -0.07
     kam
    -0.07
    ᨳ
    -0.07
     Yun
    -0.07
    开玩笑
    -0.07
    相近
    -0.07
    做出
    -0.06
    tempts
    -0.06
     Pig
    -0.06
    POSITIVE LOGITS
    Supply
    0.07
     wholesome
    0.07
    comparison
    0.06
    Inner
    0.06
    strlen
    0.06
    thumbnail
    0.06
     summ
    0.06
     Else
    0.06
    interopRequireDefault
    0.06
     Robert
    0.06
    Act Density 0.001%

    No Known Activations