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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iations
    -0.07
     Productions
    -0.07
    [group
    -0.07
    trib
    -0.06
     fmt
    -0.06
    gorithm
    -0.06
     systematic
    -0.06
     worms
    -0.06
    $m
    -0.06
     Hanson
    -0.06
    POSITIVE LOGITS
     lẫn
    0.07
    係
    0.06
     funnel
    0.06
    dın
    0.06
    清
    0.06
    /";↵
    0.06
     brand
    0.06
     删除
    0.06
    Weapons
    0.06
    dead
    0.06
    Act Density 0.019%

    No Known Activations