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

    Neuronpedia

    INDEX
    Explanations

    balance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Midwest
    -0.07
    )})↵
    -0.07
    ключен
    -0.07
     Buffalo
    -0.07
     inhibit
    -0.07
    [first
    -0.07
     servant
    -0.07
    更好
    -0.07
     cardiac
    -0.07
     besser
    -0.07
    POSITIVE LOGITS
    yen
    0.07
    荒
    0.07
    ồn
    0.07
    语音
    0.06
    𝘮
    0.06
    Genres
    0.06
     فمن
    0.06
    $img
    0.06
    ושים
    0.06
    ﱐ
    0.06
    Act Density 0.017%

    No Known Activations