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 numeric literal values—especially floating-point numbers—in XML attribute settings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    However
    -0.07
     However
    -0.06
    _gateway
    -0.06
     ram
    -0.06
    -track
    -0.06
     radius
    -0.06
     digits
    -0.06
    °C
    -0.06
     sneakers
    -0.06
     endpoint
    -0.06
    POSITIVE LOGITS
     est
    0.06
     CreateTable
    0.06
     تس
    0.06
    _goods
    0.06
    _database
    0.06
    preh
    0.06
     گو
    0.06
    ASA
    0.06
    ]='\
    0.06
     lisans
    0.06
    Act Density 0.002%

    No Known Activations