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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation or delimiters in a structured or code-like format

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

    code structure punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TokenNameLPAREN
    -0.41
    ParallelGroup
    -0.35
     extremadamente
    -0.34
    uccino
    -0.33
     perfectamente
    -0.33
     poquito
    -0.33
     <<<<<<<<<<<<<<
    -0.33
    ง่าย
    -0.32
    Temperatura
    -0.32
     Christiansen
    -0.31
    POSITIVE LOGITS
    NameInMap
    0.53
     CreateTagHelper
    0.51
     oprot
    0.50
    KommentareTeilen
    0.49
     uska
    0.49
     nakalista
    0.48
    FormTagHelper
    0.48
    addPreferredGap
    0.47
    Ɓ
    0.47
    تقاوى
    0.46
    Act Density 0.006%

    No Known Activations