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

    Neuronpedia

    INDEX
    Explanations

    Code, programming

    np_max-act · gemini-2.0-flash

    The neuron activates on dotted, CamelCase programming identifiers (e.g. namespace‐qualified class or type names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    %\
    -0.07
     fou
    -0.06
    .Auth
    -0.06
     commented
    -0.06
    这是
    -0.06
     Em
    -0.06
    ología
    -0.06
     unavailable
    -0.06
     aire
    -0.06
    Haz
    -0.06
    POSITIVE LOGITS
    agua
    0.07
     disappoint
    0.07
    -transparent
    0.06
     Ли
    0.06
     تأثیر
    0.06
    ーロ
    0.06
     فرهنگ
    0.06
     IPPROTO
    0.06
    _REAL
    0.06
    .MiddleRight
    0.06
    Act Density 0.005%

    No Known Activations