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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.75
    ◀
    -0.70
    ]")]
    -0.65
    UrlResolution
    -0.65
    /**
    -0.61
    ViewImports
    -0.60
    IsMutable
    -0.60
    SES
    -0.60
    comuna
    -0.59
    AM
    -0.59
    POSITIVE LOGITS
     <",
    0.45
     الرياضيه
    0.43
    InstrumentedTest
    0.41
     beginnetje
    0.41
    complexType
    0.35
    LogManager
    0.35
    Ссылки
    0.34
     głó
    0.33
     jinak
    0.33
    İstinadlar
    0.33
    Act Density 0.008%

    No Known Activations