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

    Neuronpedia

    INDEX
    Explanations

    Label

    np_max-act · gemini-2.0-flash

    The neuron fires on floating‐point numeric values (decimal numbers) found in XML attribute fields.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    cov
    -0.08
    _probe
    -0.07
     pol
    -0.06
    _production
    -0.06
    Tips
    -0.06
     Pow
    -0.06
    _closed
    -0.06
    .MockMvc
    -0.06
     wow
    -0.06
     threatened
    -0.06
    POSITIVE LOGITS
    Sn
    0.07
    _icon
    0.06
    780
    0.06
     Eid
    0.06
    ngine
    0.06
    	typedef
    0.06
    pling
    0.06
     executable
    0.06
     Asked
    0.06
     //
↵
↵
    0.06
    Act Density 0.003%

    No Known Activations