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

    Neuronpedia

    INDEX
    Explanations

    probability calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    حكم
    -0.07
     professionalism
    -0.06
    打扮
    -0.06
     Css
    -0.06
     vere
    -0.06
     بالإ
    -0.06
    ropical
    -0.06
     굉장
    -0.06
     exemple
    -0.06
     Sms
    -0.06
    POSITIVE LOGITS
    -author
    0.07
    开幕
    0.07
     сер
    0.07
     XP
    0.07
    Sab
    0.07
     releases
    0.06
     更新
    0.06
    ző
    0.06
    ဝ
    0.06
    进展
    0.06
    Act Density 0.002%

    No Known Activations