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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on floating-point numeric literals (decimal numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    。その
    -0.07
     GURL
    -0.07
     entityManager
    -0.06
    leftJoin
    -0.06
    龄
    -0.06
    .BindingSource
    -0.06
     isset
    -0.06
    ترك
    -0.06
    ()=="
    -0.06
     بغ
    -0.06
    POSITIVE LOGITS
     Dynam
    0.07
     Palin
    0.07
     USB
    0.06
    	hash
    0.06
     cv
    0.06
     Languages
    0.06
    .fi
    0.06
    нач
    0.06
    ysi
    0.06
     diy
    0.06
    Act Density 0.004%

    No Known Activations