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

    Neuronpedia

    INDEX
    Explanations

    drawable

    np_max-act · gemini-2.0-flash

    The neuron fires on floating-point numeric literals (decimal numbers) in XML attribute values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     kings
    -0.06
     combining
    -0.06
    Delete
    -0.06
     UI
    -0.06
     Comments
    -0.06
    	atomic
    -0.06
    }),↵
    -0.06
    Company
    -0.06
    	Common
    -0.06
    Session
    -0.06
    POSITIVE LOGITS
    drawable
    0.10
    .drawable
    0.09
     stav
    0.07
    /backend
    0.07
     پ
    0.06
    猫
    0.06
    นอ
    0.06
     drawable
    0.06
    -dev
    0.06
     우
    0.06
    Act Density 0.001%

    No Known Activations