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

    Neuronpedia

    INDEX
    Explanations

    floating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    シンプル
    -0.06
     lodged
    -0.06
    一つ
    -0.06
    תשע
    -0.06
     earliest
    -0.06
    [temp
    -0.06
     COMMENT
    -0.06
     Artem
    -0.06
     !=↵
    -0.06
     triangular
    -0.06
    POSITIVE LOGITS
    known
    0.07
    手段
    0.07
    ypass
    0.07
    率
    0.07
    Framework
    0.07
    _LA
    0.07
    糊
    0.06
    مناسب
    0.06
    modo
    0.06
    icals
    0.06
    Act Density 0.019%

    No Known Activations