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

    Neuronpedia

    INDEX
    Explanations

    terms related to confirmation or verification in technology contexts

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

    Non-English language fragments

    np_acts-logits-general · gemini-2.0-flash

    multi-word continuations or compound words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.63
     common
    -0.53
     Common
    -0.50
     va
    -0.48
     full
    -0.47
    [
    -0.47
     می‌ده
    -0.47
     .
    -0.47
     [
    -0.47
    nhold
    -0.46
    POSITIVE LOGITS
    RenderAtEndOf
    1.07
    CloseOperation
    1.01
    RectangleBorder
    0.99
     Zapo
    0.94
     myſelf
    0.93
    ContentAsync
    0.92
     betweenstory
    0.92
    +#+
    0.91
     itſelf
    0.91
     ModelExpression
    0.86
    Act Density 0.037%

    No Known Activations