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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

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

    Ends with a period

    np_acts-logits-general · gemini-2.0-flash

    beginning of lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pair
    -0.57
    letoe
    -0.55
    ​
    -0.51
    jaardag
    -0.51
     alimentaires
    -0.50
    Tren
    -0.47
     razão
    -0.47
    gameserver
    -0.47
    তথ্যসূত্র
    -0.47
    bieron
    -0.46
    POSITIVE LOGITS
    0.89
    BeginContext
    0.88
    PerformLayout
    0.81
     cherchés
    0.78
     "..\..\..\
    0.78
     للمعارف
    0.76
     autorytatywna
    0.73
     InputDecoration
    0.70
    lgari
    0.68
    новниш
    0.67
    Act Density 0.215%

    No Known Activations