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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    对手
    -0.07
     Guid
    -0.06
    Conference
    -0.06
    mpz
    -0.06
    /ros
    -0.06
     Cùng
    -0.06
     NotFoundException
    -0.06
    实施意见
    -0.06
    选用
    -0.06
    잨
    -0.06
    POSITIVE LOGITS
     произведен
    0.07
    ────────
    0.07
     emptied
    0.07
    )_
    0.07
    那是
    0.06
    QM
    0.06
    特产
    0.06
    issues
    0.06
     violate
    0.06
    .template
    0.06
    Act Density 0.002%

    No Known Activations