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

    Neuronpedia

    INDEX
    Explanations

    Narrative writing snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vanilla
    -0.07
    (language
    -0.07
    	keys
    -0.07
    .query
    -0.06
     Laure
    -0.06
    STRU
    -0.06
    ijn
    -0.06
    _IDS
    -0.06
    рупп
    -0.06
    ylum
    -0.06
    POSITIVE LOGITS
    _strike
    0.07
    (router
    0.06
    /DD
    0.06
     nw
    0.06
    .co
    0.06
    mill
    0.06
     West
    0.06
    restricted
    0.06
    대의
    0.06
    abetes
    0.06
    Act Density 0.046%

    No Known Activations