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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with language and communication

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

    words and language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.66
    RTSC
    -0.54
     ligiloj
    -0.52
    IBar
    -0.52
     propOrder
    -0.45
     Chwiliwch
    -0.45
    Rohy
    -0.45
    ConstraintMaker
    -0.43
    TableHead
    -0.43
     disponibilités
    -0.43
    POSITIVE LOGITS
     INTERESAR
    0.53
    文字
    0.50
     WORDS
    0.48
    Words
    0.48
     文字
    0.48
     verbal
    0.46
     words
    0.46
     Words
    0.45
    verbal
    0.45
     linguistic
    0.42
    Act Density 0.069%

    No Known Activations