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

    Neuronpedia

    INDEX
    Explanations

    nouns and phrases indicating action and assertiveness

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

    always always

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁢
    -0.42
    ună
    -0.42
    #
    -0.36
    yecto
    -0.35
    AndEndTag
    -0.34
    Eksteraj
    -0.33
     odkazy
    -0.33
     saudara
    -0.32
    GIVEREF
    -0.31
    SizeMode
    -0.30
    POSITIVE LOGITS
     ModelExpression
    0.65
    webElementXpaths
    0.56
    enterOuterAlt
    0.51
     CURIAM
    0.50
    RectangleBorder
    0.46
    addContainerGap
    0.45
     AppCompatTheme
    0.45
    imanapun
    0.45
     disponibilités
    0.45
    SourceChecksum
    0.45
    Act Density 0.134%

    No Known Activations