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

    Neuronpedia

    INDEX
    Explanations

    links to documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dall
    0.42
     blancs
    0.40
     banding
    0.40
     रक्
    0.40
    阙
    0.40
    ाइज
    0.39
     fainting
    0.39
    декс
    0.39
     wśród
    0.39
    POM
    0.38
    POSITIVE LOGITS
    apiVersion
    0.46
     fastapi
    0.40
    >();
    0.38
     مورد
    0.38
     साम
    0.37
    Considering
    0.35
     Igu
    0.35
    照
    0.35
    current
    0.35
    Current
    0.35
    Act Density 0.001%

    No Known Activations