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

    Neuronpedia

    INDEX
    Explanations

    blocks of code that denote the end of functions or classes

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

    protobuf serialization code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    saraba
    -0.53
    velocityX
    -0.39
     wikipagina
    -0.37
    writeFileSync
    -0.36
     onData
    -0.36
    Ecotoxicity
    -0.35
     seaborn
    -0.35
    Достоинства
    -0.34
     चीज़ों
    -0.34
    騨
    -0.34
    POSITIVE LOGITS
    WithIOException
    0.58
    ArgsConstructor
    0.57
    RUnlock
    0.48
     ProtoMessage
    0.46
    astéroïdes
    0.46
     CURIAM
    0.46
     AssemblyVersion
    0.45
    RTEX
    0.44
    farwyddwr
    0.44
    expandindo
    0.43
    Act Density 0.001%

    No Known Activations