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 activates on numeric literals (especially decimal numbers) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ("."
    -0.06
     sewage
    -0.06
    (w
    -0.06
    rowsable
    -0.06
    	assertFalse
    -0.06
    .base
    -0.06
    _organization
    -0.06
    	git
    -0.05
    ==========↵
    -0.05
     mixer
    -0.05
    POSITIVE LOGITS
    ts
    0.08
    Components
    0.07
    $product
    0.07
     dục
    0.06
    ồi
    0.06
     Atkins
    0.06
     Expenses
    0.06
     chương
    0.06
    列
    0.06
     Monk
    0.06
    Act Density 0.017%

    No Known Activations