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

    Neuronpedia

    INDEX
    Explanations

    stri

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .desc
    -0.08
     bottleneck
    -0.07
     dataset
    -0.07
    .environment
    -0.07
    人生
    -0.07
     specifics
    -0.07
    /conf
    -0.07
    .True
    -0.07
    gard
    -0.07
    _QUAL
    -0.07
    POSITIVE LOGITS
    씩
    0.07
    เผย
    0.07
    🤣
    0.07
    żu
    0.06
    豳
    0.06
    肋
    0.06
     .↵↵↵↵
    0.06
    প
    0.06
    喉
    0.06
    故意
    0.06
    Act Density 0.002%

    No Known Activations