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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly quotation marks and commas, indicating speech or dialogue

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

    Commas, periods, and quotation marks followed by common words

    np_acts-logits-general · gemini-2.0-flash

    comma or period followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jsdelivr
    -0.51
    áld
    -0.48
     jod
    -0.47
    BufferException
    -0.46
     chio
    -0.45
     hObject
    -0.45
    клопе
    -0.44
    rome
    -0.43
    bootstrapcdn
    -0.43
    BeginInit
    -0.42
    POSITIVE LOGITS
     duquel
    0.47
     الرياضيه
    0.42
     ragazze
    0.41
     mieste
    0.40
     pertanto
    0.40
     ejecutivo
    0.40
     culturelle
    0.39
     perciò
    0.39
     tué
    0.39
     görmek
    0.38
    Act Density 0.063%

    No Known Activations