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

    Neuronpedia

    INDEX
    Explanations

    elements related to data structures, specifically focusing on keys and values in mapping or JSON-like formats

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

    Non-English code or text

    np_acts-logits-general · gemini-2.0-flash

    code examples or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jelent
    -0.55
     kasarigan
    -0.53
    styrene
    -0.50
    processable
    -0.50
    vula
    -0.48
    ISH
    -0.47
    -0.47
    ঙ্গ
    -0.47
    ={{
    -0.47
    itzenden
    -0.47
    POSITIVE LOGITS
    rungsseite
    0.77
     للاسماء
    0.62
     BoxDecoration
    0.59
     handleMessage
    0.58
    HtmlAttribute
    0.57
    endpush
    0.56
     ويكيپيديا
    0.55
     ModelExpression
    0.54
     Grimal
    0.53
     سكانية
    0.51
    Act Density 0.370%

    No Known Activations