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

    Neuronpedia

    INDEX
    Explanations

    data types

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literals (especially decimal numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	Service
    -0.06
    gro
    -0.06
    heartbeat
    -0.06
     материалов
    -0.06
    AppBundle
    -0.06
     kilometres
    -0.06
     Western
    -0.06
     Penn
    -0.06
    assertSame
    -0.06
     fraternity
    -0.06
    POSITIVE LOGITS
    ΗΝ
    0.07
    _comments
    0.06
     exh
    0.06
    ARED
    0.06
    -ex
    0.06
     Anch
    0.06
    PIPE
    0.06
    OID
    0.06
     aprender
    0.06
    odu
    0.06
    Act Density 0.016%

    No Known Activations