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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Teeth
    -0.08
     youths
    -0.07
    -comments
    -0.07
     Sri
    -0.07
     oppression
    -0.07
     toolStrip
    -0.06
     ();↵
    -0.06
    毛主席
    -0.06
     Period
    -0.06
     Lyrics
    -0.06
    POSITIVE LOGITS
    обиль
    0.08
    par
    0.07
    �
    0.07
     stops
    0.07
    isFunction
    0.07
    стр
    0.07
    抢
    0.07
     energía
    0.06
    side
    0.06
    基数
    0.06
    Act Density 0.035%

    No Known Activations