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

    Neuronpedia

    INDEX
    Explanations

    bidding proposals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     schwier
    -0.09
    _proxy
    -0.09
    Proxy
    -0.09
     Proxy
    -0.09
     proxy
    -0.09
     تحويل
    -0.08
     regimes
    -0.08
     Нез
    -0.08
    .Proxy
    -0.08
     મુશ્ક
    -0.08
    POSITIVE LOGITS
     제출
    0.09
     RESPONSE
    0.09
     canned
    0.09
     submitted
    0.08
     tact
    0.08
    ponses
    0.08
    bah
    0.08
     贵
    0.08
     jars
    0.08
     кандид
    0.08
    Act Density 0.018%

    No Known Activations