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

    Neuronpedia

    INDEX
    Explanations

    punctuation or specific formatting elements in the text

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

    dates and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.36
     <<<<<<<<<<<<<<
    -0.35
     especialista
    -0.33
     pocas
    -0.32
    faßt
    -0.31
     géant
    -0.31
     specialist
    -0.30
     "..\..\..\
    -0.30
    chartInstance
    -0.29
     especialistas
    -0.29
    POSITIVE LOGITS
     kasarigan
    0.62
    Diwedd
    0.59
    night
    0.59
    GEBURTSDATUM
    0.58
    expandindo
    0.56
     שוליים
    0.56
    ôtel
    0.56
    AndEndTag
    0.55
     للمعارف
    0.53
    нгред
    0.53
    Act Density 0.061%

    No Known Activations