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

    Neuronpedia

    INDEX
    Explanations

    transparency and public accountability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Operator
    -0.07
     Fruit
    -0.07
     embassy
    -0.07
    Pag
    -0.07
    Pros
    -0.06
    Authority
    -0.06
     ^(
    -0.06
    (ast
    -0.06
    Rooms
    -0.06
     BACKGROUND
    -0.06
    POSITIVE LOGITS
    -request
    0.06
     darn
    0.06
    _TS
    0.06
    τι
    0.06
     chic
    0.06
    _ts
    0.06
    ervlet
    0.06
    rıca
    0.06
    �력
    0.06
     än
    0.06
    Act Density 0.017%

    No Known Activations