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

    Neuronpedia

    INDEX
    Explanations

    URLs and links

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

    URLs and web addresses

    np_acts-logits-general · gemini-2.0-flash

    URLs and web links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reducers
    -0.45
    =*/
    -0.44
    cuts
    -0.43
     moment
    -0.42
    ⎢
    -0.41
     Cuts
    -0.41
    地道
    -0.41
    愷
    -0.40
     attacks
    -0.40
     modding
    -0.40
    POSITIVE LOGITS
    Kaynakça
    0.54
    Наводи
    0.46
    Билгалдахарш
    0.46
    décoration
    0.45
    UseVisualStyle
    0.44
     للاسماء
    0.43
    DoubleQuotes
    0.43
    GOTREF
    0.43
    paravant
    0.41
    BeginInit
    0.40
    Act Density 0.094%

    No Known Activations