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

    Neuronpedia

    INDEX
    Explanations

    code related to database queries and email processing

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

    Code snippets' punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    code syntax elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ",{
    -0.46
     Taras
    -0.45
    mogorov
    -0.43
     régal
    -0.43
     devoir
    -0.43
    ########.
    -0.42
    ',{
    -0.42
     bieg
    -0.41
    phazard
    -0.41
     anteriore
    -0.41
    POSITIVE LOGITS
     ($
    2.00
    ($
    1.94
     [$
    1.68
    /$
    1.59
    -$
    1.57
    [$
    1.57
    =$
    1.56
    :$
    1.50
    +$
    1.48
     $
    1.47
    Act Density 0.120%

    No Known Activations