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

    Neuronpedia

    INDEX
    Explanations

    true

    np_max-act · gemini-2.0-flash

    The neuron is detecting floating-point numeric literals (decimal numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    <Result
    -0.07
    Thai
    -0.07
    بینی
    -0.07
    _"+
    -0.06
     Basics
    -0.06
     sexuality
    -0.06
    ileo
    -0.06
     `%
    -0.06
    インタ
    -0.06
    	If
    -0.06
    POSITIVE LOGITS
    AH
    0.08
    redirectToRoute
    0.07
     disagreements
    0.06
     gelir
    0.06
     λεπ
    0.06
     orderId
    0.06
     disag
    0.06
     vergi
    0.06
     없어
    0.06
     tablets
    0.06
    Act Density 0.008%

    No Known Activations