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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash

    The neuron activates whenever it sees the name of a programming language.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     three
    -0.08
     four
    -0.07
     five
    -0.07
     特
    -0.07
    qm
    -0.06
    átu
    -0.06
     strengthen
    -0.06
     tří
    -0.06
     Tournament
    -0.06
     büny
    -0.06
    POSITIVE LOGITS
    AW
    0.08
    AGAIN
    0.06
     bás
    0.06
     any
    0.06
    аліз
    0.06
    aw
    0.06
    (Index
    0.06
    ALL
    0.06
    finally
    0.06
    visibility
    0.06
    Act Density 0.037%

    No Known Activations