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

    Neuronpedia

    INDEX
    Explanations

    terms related to linguistics and kinship

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

    linguistic phenomena and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.46
    AddRef
    -0.45
    ▲
    -0.44
     consigo
    -0.42
    ">//
    -0.42
     الرياضيه
    -0.42
    ConstraintMaker
    -0.40
    circledR
    -0.40
    UseVisualStyle
    -0.40
    Recovery
    -0.40
    POSITIVE LOGITS
     linguistic
    1.70
     Linguistic
    1.64
     lingu
    1.64
    Lingu
    1.63
     linguistics
    1.62
     Lingu
    1.52
     Linguistics
    1.49
    linguistic
    1.46
    lingu
    1.41
     lingü
    1.13
    Act Density 0.003%

    No Known Activations