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

    Neuronpedia

    INDEX
    Explanations

    code and file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oven
    -0.06
     Leaf
    -0.06
    osals
    -0.06
     stones
    -0.06
     카
    -0.06
    weet
    -0.06
     IK
    -0.06
     skim
    -0.06
    Tracks
    -0.06
     produits
    -0.06
    POSITIVE LOGITS
     /
    0.10
    )/(
    0.08
    =<
    0.07
    +"/"+
    0.07
     />\
    0.07
     /↵
    0.07
     "/
    0.07
    |m
    0.07
    /B
    0.07
    /AP
    0.07
    Act Density 0.031%

    No Known Activations