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

    Neuronpedia

    INDEX
    Explanations

    snippets of programming syntax and structures, particularly in the context of object-oriented programming

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

    Integer data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.46
     Tro
    -0.44
     createState
    -0.43
     void
    -0.40
    Tro
    -0.40
    PendingIntent
    -0.40
    لاث
    -0.40
     utafitiHapana
    -0.39
    ContextHolder
    -0.38
     Segment
    -0.37
    POSITIVE LOGITS
     data
    0.56
    parsedMessage
    0.55
    data
    0.54
    ⓧ
    0.52
     données
    0.51
     newData
    0.51
     kasarigan
    0.49
    SourceChecksum
    0.47
    データを
    0.46
     مشين
    0.45
    Act Density 0.018%

    No Known Activations