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

    Neuronpedia

    INDEX
    Explanations

    numerical values in various formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numbers, often followed by other numbers

    np_acts-logits-general · gemini-2.0-flash

    face to, done by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    σσ
    -0.47
    pora
    -0.43
    anova
    -0.42
    —“
    -0.42
    livan
    -0.40
     app
    -0.40
    Herr
    -0.39
    sule
    -0.39
    xie
    -0.39
     Kale
    -0.38
    POSITIVE LOGITS
    CloseOperation
    0.84
    RenderAtEndOf
    0.81
     дописавши
    0.76
    +#+
    0.75
    AndEndTag
    0.74
    PreferredItem
    0.74
    ########.
    0.72
    UrlResolution
    0.71
    LabelTagHelper
    0.70
    AnchorTagHelper
    0.69
    Act Density 1.039%

    No Known Activations