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

    Neuronpedia

    INDEX
    Explanations

    device, Rural, Municipality, header

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ieurs
    1.32
    นาม
    1.27
    échelle
    1.23
    場合
    1.21
    紝
    1.21
    髹
    1.19
     infe
    1.19
     idées
    1.19
    lardan
    1.18
    اً
    1.18
    POSITIVE LOGITS
    eney
    1.16
    ào
    1.11
     Blender
    1.09
    ணை
    1.07
     bucks
    1.06
    וא
    1.00
    o
    0.99
    ిన
    0.97
    Heart
    0.97
     Sarge
    0.94
    Act Density 0.001%

    No Known Activations