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

    Neuronpedia

    INDEX
    Explanations

    characteristics and settings related to user interface and alert dialogs in code

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

    key:value pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <strong>
    -0.29
    Folgende
    -0.25
    ​
    -0.25
    外
    -0.24
    <em>
    -0.24
    <b>
    -0.23
    　
    -0.23
    　　
    -0.23
     worden
    -0.22
     now
    -0.22
    POSITIVE LOGITS
    sizeCache
    0.92
     AssemblyTitle
    0.92
    niſſe
    0.89
     ddelwed
    0.87
    ſammen
    0.87
     مرئيه
    0.85
    <unused8>
    0.83
     パンチラ
    0.83
    [@BOS@]
    0.83
    <unused3>
    0.83
    Act Density 0.014%

    No Known Activations