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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong emotional sentiments

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

    Follows a quotation mark

    np_acts-logits-general · gemini-2.0-flash

    punctuation and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.61
    numerusform
    -0.53
    ~~~~~~~~~~~~~~~~
    -0.47
     szczegó
    -0.47
    ese
    -0.46
     treo
    -0.45
    igi
    -0.45
     ring
    -0.45
    led
    -0.45
    ----------------
    -0.45
    POSITIVE LOGITS
    principalColumn
    0.86
    NameInMap
    0.86
    0.85
     متعلقه
    0.74
    Билгалдахарш
    0.72
     NSCoder
    0.70
    WEBPACK
    0.69
     الحره
    0.69
    phosa
    0.65
     autorytatywna
    0.65
    Act Density 0.016%

    No Known Activations