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

    Neuronpedia

    INDEX
    Explanations

    programming-related punctuation marks and syntax elements

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

    <start_of_turn>user identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.81
    iſen
    -0.71
     queſta
    -0.70
     pinulongan
    -0.70
     autorytatywna
    -0.69
     laſſen
    -0.68
    enderror
    -0.67
    ſelf
    -0.66
    ſſung
    -0.66
     imagui
    -0.65
    POSITIVE LOGITS
    ://
    0.52
    Literatuur
    0.31
    <em>
    0.31
    s
    0.30
     Fat
    0.28
     Bob
    0.28
    /
    0.28
     not
    0.27
     Typical
    0.27
     Mark
    0.27
    Act Density 0.006%

    No Known Activations