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

    Neuronpedia

    INDEX
    Explanations

    media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    粤港澳
    -0.07
    抢占
    -0.07
    残留
    -0.07
    痿
    -0.07
    留意
    -0.07
    国产
    -0.07
    珛
    -0.07
    要好好
    -0.07
     SHOW
    -0.07
    准入
    -0.07
    POSITIVE LOGITS
    .',
    0.07
     ------------------------------------------------------------
    0.07
    ANDING
    0.07
     gent
    0.07
    身旁
    0.07
    ael
    0.07
     Tip
    0.06
    nection
    0.06
    ()</
    0.06
    ****************************
    0.06
    Act Density 0.020%

    No Known Activations