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

    Neuronpedia

    INDEX
    Explanations

    references to programming syntax and structures, particularly related to code snippets

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

    special characters or hypertrophy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.58
    المناصب
    -0.52
     '\\;'
    -0.49
    يميديا
    -0.49
     bower
    -0.48
    bison
    -0.48
    ewe
    -0.47
     للاسماء
    -0.47
    presto
    -0.47
    brie
    -0.47
    POSITIVE LOGITS
    '=>$
    1.70
    "=>$
    1.28
    ='".$
    0.85
    /'.$
    0.84
     '".$
    0.72
    ']=$
    0.72
    ">'.$
    0.67
    <?=$
    0.65
    '],$
    0.62
    ="<?=$
    0.61
    Act Density 0.004%

    No Known Activations