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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     плеч
    -0.07
    �체
    -0.07
    _salary
    -0.06
    LOCATION
    -0.06
    _components
    -0.06
    idos
    -0.06
    eacher
    -0.06
    orge
    -0.06
     chef
    -0.06
    amins
    -0.06
    POSITIVE LOGITS
    Charts
    0.07
     """.
    0.07
    我们
    0.07
    ประสบ
    0.07
     dbus
    0.06
     μας
    0.06
     گفت
    0.06
     Trudeau
    0.06
     провод
    0.06
    餐
    0.06
    Act Density 0.000%

    No Known Activations