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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives related to quality or enjoyment

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

    positive adjectives followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.44
    AccessorTable
    -0.39
    帖最后由
    -0.39
     preocupes
    -0.38
    UserScript
    -0.38
    AutoScaleMode
    -0.38
    ͠
    -0.33
    Sedangkan
    -0.33
     LeBlanc
    -0.33
     lược
    -0.32
    POSITIVE LOGITS
     OFDb
    0.60
    Manbalar
    0.59
     saveiro
    0.58
     autorytatywna
    0.56
    bnf
    0.56
     ModelExpression
    0.56
    RTHOOK
    0.54
    modelBuilder
    0.54
    contentLoaded
    0.54
     Italijanski
    0.51
    Act Density 0.007%

    No Known Activations