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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron detects floating‐point numeric literals in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    leşik
    -0.07
     sonuç
    -0.06
    (integer
    -0.06
    _pel
    -0.06
    Publication
    -0.06
    (Device
    -0.06
    -drop
    -0.06
    heten
    -0.06
    ().'
    -0.06
    Mir
    -0.06
    POSITIVE LOGITS
    摩
    0.06
    وي
    0.06
     sme
    0.06
     tweeting
    0.06
    excluding
    0.06
     }}>↵
    0.06
    eacher
    0.06
    真是
    0.06
     MPEG
    0.06
    	sc
    0.06
    Act Density 0.006%

    No Known Activations