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

    Neuronpedia

    INDEX
    Explanations

    Co

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of proper‐noun organization names (e.g. companies, agencies, and institutional titles).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Sanford
    -0.06
    uzzi
    -0.06
     Rings
    -0.06
    ратно
    -0.06
    021
    -0.06
    960
    -0.06
     Duis
    -0.06
     Christopher
    -0.06
    すれば
    -0.06
     PREFIX
    -0.06
    POSITIVE LOGITS
    	rb
    0.08
    _G
    0.07
    ัจ
    0.07
     CONF
    0.07
    _P
    0.06
    -п
    0.06
    DUCT
    0.06
     перей
    0.06
     avait
    0.06
     영향을
    0.06
    Act Density 0.122%

    No Known Activations