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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to programming, especially those concerning data structures and algorithms

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

    code punctuation and operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.38
    最快更新
    -0.36
    Tikang
    -0.31
    LookAnd
    -0.28
     kimse
    -0.28
    -------
    -0.26
     testSet
    -0.26
     समीक्षाएं
    -0.26
     hâte
    -0.24
     cuánt
    -0.23
    POSITIVE LOGITS
    ロウィン
    0.69
    㤵
    0.68
    ſammen
    0.67
    ðsíða
    0.65
    <unused28>
    0.65
    <unused21>
    0.65
    <unused41>
    0.65
     ddelwed
    0.65
    <unused51>
    0.65
    [@BOS@]
    0.64
    Act Density 0.008%

    No Known Activations