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

    Neuronpedia

    INDEX
    Explanations

    sentences containing a high frequency of commas

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

    Followed by a comma

    np_acts-logits-general · gemini-2.0-flash

    unfortunately, thus, finally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.65
     مشين
    -0.47
    ________________
    -0.44
    Descripció
    -0.40
     GSC
    -0.39
    iostream
    -0.39
    ZG
    -0.38
    ™.
    -0.38
    তথ্যসূত্র
    -0.38
     interro
    -0.37
    POSITIVE LOGITS
    躇
    0.59
     kasarigan
    0.58
     fédé
    0.55
    queryInterface
    0.54
     the
    0.54
    brigens
    0.53
     verhe
    0.52
     Daß
    0.51
    leggen
    0.51
    kadang
    0.50
    Act Density 0.374%

    No Known Activations