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

    Neuronpedia

    INDEX
    Explanations

    JavaDoc-style or code documentation-style annotations

    oai_token-act-pair · gemini-2.0-flash

    @

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    holen
    -0.49
     parseFrom
    -0.41
    pill
    -0.38
     padres
    -0.37
     rescue
    -0.37
     prepares
    -0.37
     bouton
    -0.36
    żli
    -0.36
    казать
    -0.35
    [['
    -0.35
    POSITIVE LOGITS
    SourceChecksum
    1.03
    Personensuche
    0.81
     estekak
    0.81
     مرئيه
    0.77
     Leid
    0.68
    AndEndTag
    0.66
     disambiguazione
    0.65
     AssemblyCulture
    0.65
    omock
    0.63
     المعيارى
    0.61
    Act Density 0.181%

    No Known Activations