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

    Neuronpedia

    INDEX
    Explanations

    Matt Reeves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     политики
    0.38
    議員
    0.36
    Biden
    0.34
     სახელმწიფ
    0.34
     constitutional
    0.33
     bureaucratic
    0.33
    人間の
    0.32
    経済
    0.32
     liberalization
    0.32
    மனித
    0.32
    POSITIVE LOGITS
     同时
    0.34
     guys
    0.34
    比赛
    0.33
     trying
    0.32
     Manager
    0.32
     tries
    0.32
     Trying
    0.32
     Championships
    0.31
     ครั้ง
    0.31
     balls
    0.30
    Act Density 0.000%

    No Known Activations