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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on Python type‐annotation tokens (e.g. Optional, Iterable, List, dict, Any, and other annotated types).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    }`).
    -0.08
    tracked
    -0.07
     Німеч
    -0.07
    ่อง
    -0.07
    akk
    -0.06
     errmsg
    -0.06
    .)↵
    -0.06
     нер
    -0.06
     Bard
    -0.06
    olf
    -0.06
    POSITIVE LOGITS
    .Rec
    0.06
    omidou
    0.06
     مقدم
    0.06
    _MONTH
    0.06
    (deck
    0.06
     prosec
    0.06
    .GeneratedValue
    0.06
     разм
    0.06
    　　 　 　
    0.05
     progressBar
    0.05
    Act Density 0.533%

    No Known Activations