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

    Neuronpedia

    INDEX
    Explanations

    syntactic markers and punctuation that indicate sentence structure and flow

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

    proper nouns followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.68
     slick
    -0.63
     propOrder
    -0.62
     ujednoznacz
    -0.59
    pgterms
    -0.58
    الحياه
    -0.56
    XtraReports
    -0.55
     informée
    -0.54
     criss
    -0.54
    jspb
    -0.53
    POSITIVE LOGITS
     abstrato
    0.45
     geométrico
    0.45
    protetor
    0.44
     demikian
    0.44
     recours
    0.42
     shall
    0.42
     laikā
    0.42
    guisement
    0.41
     således
    0.40
     Furthermore
    0.40
    Act Density 0.046%

    No Known Activations