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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    限制
    -0.07
    rms
    -0.07
    IData
    -0.07
     PAC
    -0.06
    .idea
    -0.06
    غم
    -0.06
     nurt
    -0.06
     Spain
    -0.06
    َب
    -0.06
    لب
    -0.06
    POSITIVE LOGITS
     Demon
    0.07
    [↵
    0.06
    ($('
    0.06
     Brazilian
    0.06
    ){}↵
    0.06
     Carolina
    0.06
    -secondary
    0.06
     vám
    0.06
    .*/↵
    0.06
    *S
    0.06
    Act Density 0.002%

    No Known Activations