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

    Neuronpedia

    INDEX
    Explanations

    common words and expressions related to asking for help or support

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

    Code, foreign languages, or unusual characters

    np_acts-logits-general · gemini-2.0-flash

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.78
     “
    -0.69
     "
    -0.67
     a
    -0.66
     sub
    -0.62
     «
    -0.62
     (
    -0.58
     re
    -0.58
     com
    -0.57
    -
    -0.55
    POSITIVE LOGITS
    Personendaten
    1.19
     giapp
    1.15
     ویکی‌پدی
    1.11
     scolaires
    1.10
     fermés
    1.06
     avoient
    1.05
     ainfi
    1.03
     للمعارف
    1.03
     titolata
    1.02
     feroit
    1.01
    Act Density 0.048%

    No Known Activations