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

    Neuronpedia

    INDEX
    Explanations

    syntax elements and state management keywords in programming code

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

    previously/previous state updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Audiodateien
    -0.63
     հղումներ
    -0.60
    CppCodeGen
    -0.57
    WithIOException
    -0.55
    IVEREF
    -0.54
     Lordships
    -0.53
     noDo
    -0.53
    zzleHttp
    -0.52
    脚注の使い方
    -0.50
    polski
    -0.47
    POSITIVE LOGITS
     previously
    0.68
     Previously
    0.61
     previous
    0.60
     prev
    0.59
    Previously
    0.57
     Prev
    0.57
    prev
    0.54
    previously
    0.54
     sebelumnya
    0.52
     PREVIOUS
    0.52
    Act Density 0.001%

    No Known Activations