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

    Neuronpedia

    INDEX
    Explanations

    place names and nationalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    茆
    1.23
    लेकिन
    1.15
     लेकिन
    1.12
    操控
    1.03
    石头
    0.96
    所以
    0.96
    可以
    0.94
     և
    0.92
    ण्डल
    0.92
    䉍
    0.90
    POSITIVE LOGITS
    :
    1.42
    -
    1.27
    V
    1.23
    B
    1.16
    _
    1.15
    W
    1.13
    u
    1.09
    P
    1.05
    Z
    1.04
    T
    1.02
    Act Density 0.137%

    No Known Activations