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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    startswith
    -0.07
     TCHAR
    -0.07
     undermined
    -0.07
    حما
    -0.06
     göre
    -0.06
     Abu
    -0.06
    inine
    -0.06
    湯
    -0.06
    Amb
    -0.06
     Ahmad
    -0.06
    POSITIVE LOGITS
    vider
    0.07
     cinemat
    0.07
     сос
    0.07
     البع
    0.07
     earlier
    0.07
     akt
    0.07
     khấu
    0.07
     запрос
    0.07
     colle
    0.06
     opendir
    0.06
    Act Density 0.003%

    No Known Activations