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

    Neuronpedia

    INDEX
    Explanations

    Haskell IO/Future code

    np_max-act · gemini-2.0-flash

    This neuron activates on type signatures and identifiers of effectful monadic operations (e.g. IO, Future, or other effect‐container types).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -scenes
    -0.07
    .service
    -0.07
    =center
    -0.07
     Tri
    -0.06
    方面
    -0.06
    /light
    -0.06
     구성
    -0.06
    เหน
    -0.06
     Que
    -0.06
    ######↵
    -0.06
    POSITIVE LOGITS
    YW
    0.07
    :border
    0.06
    _AXIS
    0.06
    词
    0.06
     Νο
    0.06
    unuz
    0.06
    갤
    0.06
    標準
    0.06
     exe
    0.06
     ↔
    0.06
    Act Density 0.003%

    No Known Activations