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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash

    This neuron activates on HTML markup elements, especially opening tag delimiters and tag names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Performance
    -0.07
     svého
    -0.06
    -generation
    -0.06
    AV
    -0.06
     Evropy
    -0.06
     warfare
    -0.06
    quez
    -0.06
    av
    -0.06
    ContentPane
    -0.06
    ynomials
    -0.06
    POSITIVE LOGITS
     osc
    0.07
     polite
    0.06
     sean
    0.06
    mad
    0.06
    .const
    0.06
    .nick
    0.06
     {};
    0.06
    endors
    0.06
     WX
    0.06
    tesy
    0.06
    Act Density 0.006%

    No Known Activations