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

    Neuronpedia

    INDEX
    Explanations

    Chinese names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Afric
    0.79
     हिन्द
    0.77
     Indies
    0.77
     Mediterr
    0.67
     Eureka
    0.67
     Caribbean
    0.66
     Arctic
    0.65
     BIP
    0.65
    ibil
    0.63
     confl
    0.63
    POSITIVE LOGITS
     Wang
    2.55
     Zhang
    2.39
     Liu
    2.28
    Wang
    2.25
    Zhang
    2.21
     Chen
    2.14
     Zhao
    2.12
     Zhou
    2.08
     Li
    2.07
    Liu
    2.04
    Act Density 0.014%

    No Known Activations