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

    Neuronpedia

    INDEX
    Explanations

    code and configuration files

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literals (integers and decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ();++
    -0.06
    선을
    -0.06
    ..↵↵
    -0.06
    _emlrt
    -0.06
     dicks
    -0.06
    才
    -0.06
    ems
    -0.06
    912
    -0.06
     October
    -0.06
     Lakers
    -0.06
    POSITIVE LOGITS
    	has
    0.08
    shint
    0.08
     Goals
    0.07
    CUR
    0.07
    아파트
    0.07
    ilog
    0.07
    .getLast
    0.07
    nox
    0.07
    하지
    0.07
    empt
    0.07
    Act Density 1.124%

    No Known Activations