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

    Neuronpedia

    INDEX
    Explanations

    code structure and syntax elements in programming languages

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

    .trim adds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     include
    -0.30
     conto
    -0.29
     cose
    -0.29
    ↵
    -0.28
     this
    -0.28
     assi
    -0.28
     here
    -0.27
     ве
    -0.26
     even
    -0.25
     while
    -0.25
    POSITIVE LOGITS
     فريبيس
    0.86
    RenderAtEndOf
    0.84
    MessageTagHelper
    0.84
    contentLoaded
    0.82
    ſicht
    0.79
     invokingState
    0.78
    Personendaten
    0.78
     パンチラ
    0.76
    <unused52>
    0.75
    [@BOS@]
    0.75
    Act Density 0.159%

    No Known Activations