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

    Neuronpedia

    INDEX
    Explanations

    geometry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Italia
    -0.07
    立刻
    -0.07
    ครอง
    -0.06
    ItemType
    -0.06
    背
    -0.06
     채
    -0.06
     продовж
    -0.06
     journal
    -0.06
     Italians
    -0.06
     commute
    -0.06
    POSITIVE LOGITS
    181
    0.07
    ой
    0.06
     Twin
    0.06
    Desktop
    0.06
    탕
    0.06
    redentials
    0.06
     diversos
    0.06
    Rep
    0.06
    pais
    0.06
    _REC
    0.06
    Act Density 0.007%

    No Known Activations