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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics

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

    numbers and percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crystals
    -0.31
     consequ
    -0.31
     jemals
    -0.31
     Races
    -0.30
    躇
    -0.29
     dudas
    -0.29
    woordig
    -0.29
     zorg
    -0.29
    kawi
    -0.29
    :['
    -0.28
    POSITIVE LOGITS
     مشين
    0.77
    :✨
    0.77
     Taktlose
    0.73
     Exactos
    0.59
     PeEnEo
    0.59
     ExecuteAsync
    0.57
    fromnode
    0.57
    0.57
    IsMutable
    0.57
    UnusedPrivate
    0.56
    Act Density 0.271%

    No Known Activations