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

    Neuronpedia

    INDEX
    Explanations

    first person pronouns or references, sometimes in questions

    oai_token-act-pair · gemini-2.0-flash

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InSection
    -0.66
    PerformLayout
    -0.66
    Touches
    -0.63
    NewReader
    -0.61
    ."</
    -0.60
    AddHtmlAttribute
    -0.59
    ftagPool
    -0.59
     she
    -0.59
    awtextra
    -0.58
    ?")
    -0.57
    POSITIVE LOGITS
    mainAxisSize
    0.54
    ThemeOverlay
    0.45
     '\\;'
    0.45
     Socialista
    0.44
     indietro
    0.44
     pesante
    0.44
    ьаж
    0.43
    zugs
    0.42
    AnchorTagHelper
    0.42
     Plow
    0.42
    Act Density 4.254%

    No Known Activations