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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IMPLIED
    -0.07
    createdAt
    -0.07
    控
    -0.07
    Coll
    -0.07
    -0.07
     lon
    -0.07
     Som
    -0.07
    COVID
    -0.07
     REUTERS
    -0.07
     ApplicationException
    -0.07
    POSITIVE LOGITS
    /login
    0.06
    ARTH
    0.06
     ""))↵
    0.06
    >r
    0.06
     wheels
    0.06
    periments
    0.06
     togg
    0.06
    (deg
    0.06
    )).↵
    0.06
     ])↵
    0.05
    Act Density 0.016%

    No Known Activations