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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas and parentheses

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

    punctuation followed by descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.79
     Photocase
    -0.74
     GenerationType
    -0.68
     الحره
    -0.61
    Personensuche
    -0.61
    liferay
    -0.59
     wireType
    -0.58
    ImageContext
    -0.57
     AppCompatTheme
    -0.56
     utafitiHapana
    -0.56
    POSITIVE LOGITS
     которыми
    0.37
     яких
    0.35
     overseen
    0.34
     which
    0.34
     sitesinde
    0.33
     amely
    0.33
     largely
    0.33
    Titled
    0.33
    reszcie
    0.32
     solidly
    0.32
    Act Density 0.043%

    No Known Activations