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

    Neuronpedia

    INDEX
    Explanations

    closing curly braces in code snippets

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

    math delimiters or code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ctron
    -0.59
    évaluateur
    -0.58
    betic
    -0.56
    leck
    -0.56
    lieve
    -0.55
    buro
    -0.55
    borne
    -0.54
     CIE
    -0.54
     Brill
    -0.54
    brill
    -0.53
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.52
    Hochspringen
    0.51
    __":
    0.47
     }.
    0.47
    Tembelea
    0.47
    //</
    0.46
     تضيفلها
    0.45
    //}
    0.44
     productivo
    0.44
     endwhile
    0.44
    Act Density 0.016%

    No Known Activations