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

    Neuronpedia

    INDEX
    Explanations

    present

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    idente
    -0.07
     Bingo
    -0.06
     Regions
    -0.06
    _strategy
    -0.06
     Brick
    -0.06
    .the
    -0.06
     Kabul
    -0.06
     Planning
    -0.06
     Browser
    -0.06
     washing
    -0.06
    POSITIVE LOGITS
    anth
    0.06
     yavaş
    0.06
     може
    0.06
    emark
    0.06
     CharSet
    0.06
    eware
    0.06
    ित
    0.06
    .record
    0.06
     pose
    0.06
    jylland
    0.06
    Act Density 0.005%

    No Known Activations