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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific numeric values and their relationships in contexts involving data or analysis

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

    dates and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.47
    JsonPropertyName
    -0.46
    writeField
    -0.45
     himſelf
    -0.43
     ſhe
    -0.42
    Disliked
    -0.42
     ſol
    -0.42
     تضيفلها
    -0.41
     quæ
    -0.41
    acyjna
    -0.40
    POSITIVE LOGITS
    Diweddarwch
    0.48
    χρι
    0.46
    Diwedd
    0.41
    uche
    0.40
    PREVIOUS
    0.40
    先
    0.40
     préc
    0.39
     PREVIOUS
    0.38
    المراجع
    0.38
    itter
    0.38
    Act Density 0.746%

    No Known Activations