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

    Neuronpedia

    INDEX
    Explanations

    UI elements

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens that are names of UI component classes or framework controls.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ↵↵↵↵↵↵↵↵↵
    -0.06
     gameObject
    -0.06
    Mrs
    -0.06
     lure
    -0.06
     acceleration
    -0.06
     compounds
    -0.06
     resin
    -0.06
    wife
    -0.06
    Formatter
    -0.06
    ceptor
    -0.06
    POSITIVE LOGITS
    _lazy
    0.07
    etest
    0.06
    tras
    0.06
    mlx
    0.06
     ск
    0.06
    人民
    0.06
     هو
    0.06
    �
    0.06
     �
    0.06
    jsonp
    0.06
    Act Density 0.034%

    No Known Activations