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

    Neuronpedia

    INDEX
    Explanations

    cross-comp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    视
    -0.07
    腾
    -0.06
    牛
    -0.06
    tele
    -0.06
    ਸ
    -0.06
    惭
    -0.06
    ()]);↵
    -0.06
     vowed
    -0.06
    Solution
    -0.06
     Bull
    -0.06
    POSITIVE LOGITS
     inherits
    0.08
     gid
    0.08
    .cvtColor
    0.08
    。↵↵↵↵↵↵
    0.08
    heim
    0.08
    掾
    0.07
     aos
    0.07
     администра
    0.07
    ają
    0.07
    ">

↵
    0.07
    Act Density 0.004%

    No Known Activations