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

    Neuronpedia

    INDEX
    Explanations

    code snippets and equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    好奇心
    -0.08
    低声
    -0.07
    这儿
    -0.07
    ешь
    -0.07
     Log
    -0.07
    aptors
    -0.07
    łatw
    -0.07
    (dialog
    -0.06
    ידוע
    -0.06
    了一句
    -0.06
    POSITIVE LOGITS
    פי
    0.07
    ⛽
    0.07
    Enemy
    0.07
    yii
    0.06
    🏁
    0.06
     INTERNAL
    0.06
    	utils
    0.06
    GF
    0.06
     feeds
    0.06
    [],
    0.06
    Act Density 0.073%

    No Known Activations