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

    Neuronpedia

    INDEX
    Explanations

    selected for its purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endaftaran
    0.55
    ais
    0.52
    ッシュ
    0.51
     finances
    0.49
    amia
    0.48
    ıdır
    0.48
     fiabilité
    0.47
     estadounidenses
    0.47
     cifras
    0.47
    ofi
    0.47
    POSITIVE LOGITS
    GAN
    0.52
     spool
    0.49
     सीखते
    0.48
    сь
    0.46
    Gpio
    0.45
    G
    0.45
    用来
    0.45
    Parser
    0.44
    ApiClient
    0.44
    Gan
    0.44
    Act Density 0.027%

    No Known Activations