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

    Neuronpedia

    INDEX
    Explanations

    references to code snippets, commands, or functionality instructions

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

    "A:" followed by conversational text

    np_acts-logits-general · gemini-2.0-flash

    "am ", "you ", "You "

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.85
    balleur
    -0.72
     Italijani
    -0.72
    -0.71
    majánló
    -0.69
     يتيمه
    -0.68
     Мексичка
    -0.66
     Lightboxes
    -0.65
    writeFieldEnd
    -0.64
    GEBURTSDATUM
    -0.63
    POSITIVE LOGITS
    UnusedPrivate
    0.34
     ModelExpression
    0.33
     Revisited
    0.29
    rxjs
    0.29
     pal
    0.28
    charest
    0.28
     auto
    0.27
     Feld
    0.26
     reborn
    0.26
     <<
    0.26
    Act Density 0.086%

    No Known Activations