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

    Neuronpedia

    INDEX
    Explanations

    date/time formats and regex

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    评审
    -0.08
     mercy
    -0.08
    决心
    -0.07
     trải
    -0.07
    fed
    -0.07
    .dropout
    -0.07
     advocating
    -0.07
    getFullYear
    -0.07
    追
    -0.07
     serve
    -0.07
    POSITIVE LOGITS
     sürekli
    0.08
     waking
    0.07
     objectively
    0.07
    (offset
    0.07
     //
    0.07
    .initial
    0.06
    оказ
    0.06
    _match
    0.06
    监视
    0.06
    ––
    0.06
    Act Density 0.004%

    No Known Activations