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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly semicolons and periods

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

    break

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.76
     للمعارف
    -0.75
     ſche
    -0.70
     ſch
    -0.70
     informée
    -0.69
     esternos
    -0.68
    ſelf
    -0.68
     ſur
    -0.66
     Normdatei
    -0.66
     صوتيه
    -0.65
    POSITIVE LOGITS
     tetto
    0.29
     beraber
    0.28
    て
    0.27
     querr
    0.27
     μετά
    0.27
    után
    0.27
    เอง
    0.27
     než
    0.27
     carico
    0.26
    MethodManager
    0.26
    Act Density 0.159%

    No Known Activations