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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations or symbols

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

    superscript indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.57
    GEBURTSDATUM
    -0.57
     تضيفلها
    -0.56
     CanadaChoose
    -0.56
    tagHelperRunner
    -0.48
     paille
    -0.46
    ltä
    -0.42
    الحياه
    -0.41
    CheckBreak
    -0.41
    Rhestr
    -0.41
    POSITIVE LOGITS
     }^{
    1.08
     ^{
    0.59
    |^{
    0.57
     CommandType
    0.57
    ^{
    0.55
    }}^{
    0.54
     }^{\
    0.54
    \}^{
    0.54
     $^{
    0.54
     pseudo
    0.53
    Act Density 0.004%

    No Known Activations