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

    Neuronpedia

    INDEX
    Explanations

    references to singular or single entities within various contexts

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

    single unit or entity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TProtocol
    -0.54
    ఔ
    -0.47
     AssemblyVersion
    -0.46
    istoitu
    -0.45
    的他
    -0.44
    DeleteBehavior
    -0.44
     nakalista
    -0.44
     bağlantılar
    -0.43
    PreInfinity
    -0.43
    цездатний
    -0.43
    POSITIVE LOGITS
    simult
    0.52
    SequentialGroup
    0.45
     aynı
    0.44
     together
    0.43
    :✨
    0.43
     simultaneous
    0.41
    Simult
    0.41
     Simultaneous
    0.41
     simultaneously
    0.39
    racuse
    0.39
    Act Density 0.108%

    No Known Activations