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

    Neuronpedia

    INDEX
    Explanations

    instances of quotation marks and references to images

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

    formatting, references, and images

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -1.00
     ivelany
    -0.86
     betweenstory
    -0.85
    GEBURTSDATUM
    -0.85
    transQ
    -0.85
     EconPapers
    -0.83
    bootstrapcdn
    -0.83
     $_(
    -0.80
     Autorizaciones
    -0.80
    -0.80
    POSITIVE LOGITS
    .
    0.49
    al
    0.33
    ;
    0.32
                        
    0.29
    ,
    0.29
    1
    0.28
    2
    0.28
    ↵↵
    0.28
     le
    0.27
    ↵
    0.27
    Act Density 0.001%

    No Known Activations