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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their associated structures in text

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

    closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ComVisible
    -0.68
    quelize
    -0.64
     ब्रेकडाउन
    -0.63
    ContentAlignment
    -0.63
    oa̍t
    -0.62
    GEBURTSDATUM
    -0.61
     Савезне
    -0.60
    сылкі
    -0.57
     للاسماء
    -0.56
    цездатний
    -0.56
    POSITIVE LOGITS
    ».
    0.55
    》.
    0.53
    '.
    0.53
    ’.
    0.51
    ').
    0.51
    +'.
    0.51
    .'.
    0.50
    .).
    0.50
    «.
    0.50
    '].
    0.47
    Act Density 0.013%

    No Known Activations