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

    Neuronpedia

    INDEX
    Explanations

    first person pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     possession
    -0.06
    	Http
    -0.06
    -tooltip
    -0.06
    	array
    -0.06
    headline
    -0.06
    тий
    -0.06
     pocket
    -0.06
     örgüt
    -0.06
    	include
    -0.06
     fashionable
    -0.06
    POSITIVE LOGITS
    ektor
    0.07
     introducing
    0.07
     FAQ
    0.07
    ร
    0.07
    _LOOK
    0.07
    ,S
    0.06
    :UI
    0.06
    ğiz
    0.06
     urges
    0.06
     volunteers
    0.06
    Act Density 0.080%

    No Known Activations