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

    Neuronpedia

    INDEX
    Explanations

    exhaust

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    福利
    -0.08
     البي
    -0.07
     downside
    -0.07
     الظ
    -0.07
     方
    -0.07
     기타
    -0.06
     milestone
    -0.06
    相信
    -0.06
     μεταξύ
    -0.06
     Πολ
    -0.06
    POSITIVE LOGITS
     exhausting
    0.07
     exhausted
    0.07
     exhaustion
    0.07
     aborted
    0.06
    _STATS
    0.06
    orners
    0.06
     exhaustive
    0.06
     Ens
    0.06
    HU
    0.06
     خور
    0.06
    Act Density 0.003%

    No Known Activations