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

    Neuronpedia

    INDEX
    Explanations

    Code imports

    np_max-act · gemini-2.0-flash

    The neuron is highly responsive to Python source‐code tokens—especially import/from statements, class/def keywords, and associated identifiers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     save
    -0.07
    .;
    -0.07
    .provider
    -0.07
    .Import
    -0.07
    dump
    -0.06
     spray
    -0.06
    basic
    -0.06
     Wired
    -0.06
    .dict
    -0.06
    类型
    -0.06
    POSITIVE LOGITS
     saint
    0.07
    ンパ
    0.06
     รอบ
    0.06
    otten
    0.06
     aug
    0.06
    ¨¨
    0.06
    _INTERRUPT
    0.06
    (Stream
    0.06
     NotFound
    0.06
     neut
    0.06
    Act Density 0.044%

    No Known Activations