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

    Neuronpedia

    INDEX
    Explanations

    property

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ành
    -0.07
    Using
    -0.07
    равиль
    -0.07
    Match
    -0.06
    assador
    -0.06
     完
    -0.06
     Hort
    -0.06
    κ
    -0.06
    oid
    -0.06
    ライ
    -0.06
    POSITIVE LOGITS
    (station
    0.06
    .feature
    0.06
     ores
    0.06
    Cycle
    0.06
    shield
    0.06
    -nine
    0.06
    italic
    0.06
     культуры
    0.06
     INTERRU
    0.06
     clutter
    0.06
    Act Density 0.002%

    No Known Activations