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

    Neuronpedia

    INDEX
    Explanations

    data, input, identified

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     offsetY
    0.50
     AGS
    0.47
    蛛
    0.46
     dakkh
    0.45
     Commissary
    0.44
     Ammo
    0.44
     offsetX
    0.44
     Missile
    0.44
    ونها
    0.43
    حول
    0.43
    POSITIVE LOGITS
     veja
    0.47
     engaged
    0.46
    JW
    0.45
     jaką
    0.45
     hand
    0.44
     виконав
    0.44
     przest
    0.44
    ující
    0.43
     conversation
    0.43
    J
    0.43
    Act Density 0.001%

    No Known Activations