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

    Neuronpedia

    INDEX
    Explanations

    C/C++ code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acious
    -0.07
    perate
    -0.07
    قاع
    -0.06
    トイ
    -0.06
    银川
    -0.06
    燥
    -0.06
    DataTask
    -0.06
    asive
    -0.06
     compassionate
    -0.06
    バレ
    -0.06
    POSITIVE LOGITS
     Pamela
    0.07
    网站地图
    0.07
    	help
    0.07
    ✦
    0.07
     abbrev
    0.07
    _details
    0.07
    统一
    0.07
    …”↵↵
    0.06
    #define
    0.06
     Tests
    0.06
    Act Density 0.018%

    No Known Activations