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

    Neuronpedia

    INDEX
    Explanations

    numerical data or specific numeric references within the text

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

    Numbers within parentheses

    np_acts-logits-general · gemini-2.0-flash

    parentheses with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    -0.51
    ↵↵
    -0.50
     da
    -0.50
    한
    -0.49
     le
    -0.49
     i
    -0.48
     Le
    -0.48
     w
    -0.48
     I
    -0.48
     par
    -0.48
    POSITIVE LOGITS
    StoreMessageInfo
    0.90
     jScrollPane
    0.85
     Theſe
    0.79
     itſelf
    0.78
    queryInterface
    0.78
    AxisAlignment
    0.75
    verifyException
    0.74
     ब्रेकडाउन
    0.73
    ߝ
    0.71
    ſelves
    0.70
    Act Density 0.584%

    No Known Activations