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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     폭
    -0.07
    戴
    -0.07
    сии
    -0.07
    ultimo
    -0.06
     吉
    -0.06
    (pl
    -0.06
     drama
    -0.06
    软
    -0.06
    伊
    -0.06
     gaps
    -0.06
    POSITIVE LOGITS
    :)];↵
    0.07
     Huntington
    0.07
    PIPE
    0.06
    _FIRE
    0.06
    acağ
    0.06
    ceipt
    0.06
    _SETTINGS
    0.06
    (tid
    0.06
     Miche
    0.06
    	ON
    0.06
    Act Density 0.032%

    No Known Activations