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

    Neuronpedia

    INDEX
    Explanations

    lane change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ARD
    0.47
     DK
    0.46
     ricord
    0.45
     الأكثر
    0.44
    AR
    0.43
    DK
    0.43
     réfléch
    0.42
    JSON
    0.42
     spoj
    0.42
    PLANE
    0.42
    POSITIVE LOGITS
    紧张
    0.41
     Спорттук
    0.41
    opadhyay
    0.41
    pesar
    0.41
    嬅
    0.40
    アイドル
    0.40
     નહીં
    0.39
     ಒಬ್ಬ
    0.39
    櫛
    0.38
     ఒక
    0.38
    Act Density 0.007%

    No Known Activations