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

    Neuronpedia

    INDEX
    Explanations

    nested structures or function calls in code

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

    Code containing parentheses

    np_acts-logits-general · gemini-2.0-flash

    programming variables and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Board
    -0.61
     board
    -0.57
     Can
    -0.56
     Ann
    -0.54
    ito
    -0.54
    -
    -0.53
     Sang
    -0.53
     can
    -0.53
     M
    -0.52
     May
    -0.51
    POSITIVE LOGITS
    曖昧さ回避
    1.06
    Хьажоргаш
    1.03
     externi
    1.02
    UnusedPrivate
    0.98
    Vidite
    0.96
    yntaxException
    0.91
     CURIAM
    0.91
     متعلقه
    0.87
     متحده
    0.84
    Autoritní
    0.84
    Act Density 0.206%

    No Known Activations