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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     copied
    -0.07
    .getUserName
    -0.07
     sos
    -0.07
    οκ
    -0.07
    想
    -0.06
    entialAction
    -0.06
    .players
    -0.06
    /location
    -0.06
     pent
    -0.06
    Dict
    -0.06
    POSITIVE LOGITS
     Observatory
    0.06
     gef
    0.06
    plitude
    0.06
     начинает
    0.06
    belongs
    0.06
     대한민국
    0.06
     filib
    0.06
    .Require
    0.06
     menggunakan
    0.06
     볼
    0.06
    Act Density 0.031%

    No Known Activations