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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.77
    AddHtmlAttribute
    -0.53
    noinspection
    -0.44
     Lightboxes
    -0.44
    DeleteBehavior
    -0.43
    umoj
    -0.41
     händer
    -0.41
     werdet
    -0.41
    ěstí
    -0.40
    aternion
    -0.39
    POSITIVE LOGITS
    tagHelperRunner
    0.71
    makeText
    0.55
     الحره
    0.50
    ]--;
    0.47
    SuspendLayout
    0.46
    providedIn
    0.45
    TagHelper
    0.45
     @"/
    0.45
    UnifiedTopology
    0.44
    XmlType
    0.44
    Act Density 1.663%

    No Known Activations