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

    Neuronpedia

    INDEX
    Explanations

    claim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蜘蛛
    -0.06
     sed
    -0.06
     neutral
    -0.06
    Chance
    -0.06
    Limits
    -0.06
    	cc
    -0.06
    phase
    -0.06
     Carter
    -0.06
    BoundingBox
    -0.06
     eof
    -0.06
    POSITIVE LOGITS
     quảng
    0.07
    AINED
    0.07
     श
    0.06
    �
    0.06
     blaze
    0.06
     proclaim
    0.06
     exhibiting
    0.06
    ONT
    0.06
    ```
    0.06
    ROOM
    0.06
    Act Density 0.003%

    No Known Activations