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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their surrounding punctuation or formatting

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

    Numbers followed by other numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers like nineteen, twenty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MethodManager
    -0.76
    ChildIndex
    -0.61
     مواليد
    -0.60
    Билгалдахарш
    -0.60
     PeEnEo
    -0.57
     xii
    -0.54
    lactin
    -0.51
    ptonshire
    -0.51
    HostException
    -0.51
     мәкал
    -0.51
    POSITIVE LOGITS
     nineteen
    0.69
     twentieth
    0.63
     Twenty
    0.62
     eighteen
    0.61
     Twentieth
    0.60
    :✨
    0.58
    IsMutable
    0.57
     nineteenth
    0.57
     २०
    0.56
     veinte
    0.55
    Act Density 0.586%

    No Known Activations