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

    Neuronpedia

    INDEX
    Explanations

    elements related to data structure and API request formatting

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

    Code or data structures

    np_acts-logits-general · gemini-2.0-flash

    code separators and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.66
     ModelRenderer
    -0.59
    EditorBrowsable
    -0.59
     "/";
    -0.59
     ;
    -0.58
    Shot
    -0.57
     correctes
    -0.57
     surla
    -0.57
     ModelExpression
    -0.56
     Paglinawan
    -0.56
    POSITIVE LOGITS
    !,
    0.71
    **,
    0.66
    ³,
    0.63
    ?,
    0.63
    ++,
    0.62
    ,
    0.62
    !!,
    0.62
    </caption>
    0.61
     ...,
    0.60
     however
    0.59
    Act Density 0.114%

    No Known Activations