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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical proofs and concepts

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

    probability, arithmetic, Boolean, random, circuit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Taktlose
    -0.42
    esgue
    -0.41
    IntoConstraints
    -0.40
     ujednoznacz
    -0.40
    蚪
    -0.40
    SBATCH
    -0.39
    chequer
    -0.39
    dorff
    -0.38
    PoolSize
    -0.37
     désolés
    -0.35
    POSITIVE LOGITS
    aarrggbb
    0.61
     InputDecoration
    0.54
    CppCodeGen
    0.51
    thums
    0.48
    GraphicsUnit
    0.46
     sumpay
    0.44
     nahilalakip
    0.43
    chowa
    0.43
    parsedMessage
    0.43
     meta
    0.42
    Act Density 0.961%

    No Known Activations