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

    Neuronpedia

    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash

    errors related to software code and debugging.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is tuned to pick out numeric literals (digits, including integers and floating-point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    @Spring
    -0.07
    貨
    -0.07
    ountain
    -0.06
     radians
    -0.06
    框
    -0.06
     juices
    -0.06
    _ME
    -0.06
    čení
    -0.06
     NOTICE
    -0.06
     sentencing
    -0.06
    POSITIVE LOGITS
    /channel
    0.07
    ①
    0.06
    (cn
    0.06
     RecognitionException
    0.06
    rze
    0.06
    .lastName
    0.06
    >{↵
    0.06
     �
    0.06
     configFile
    0.06
    InnerHTML
    0.06
    Act Density 0.039%

    No Known Activations