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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stimulating
    -0.07
     slower
    -0.06
     promoters
    -0.06
    visions
    -0.06
    samp
    -0.06
    "When
    -0.06
     Demp
    -0.06
    مي
    -0.06
    alias
    -0.06
    -loaded
    -0.06
    POSITIVE LOGITS
    医疗
    0.07
     Corporate
    0.07
     اجتماع
    0.06
     rủi
    0.06
     Cumhurbaş
    0.06
    자동
    0.06
     Hilton
    0.06
     yasal
    0.06
     telah
    0.06
     价格
    0.06
    Act Density 0.000%

    No Known Activations