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

    Neuronpedia

    INDEX
    Explanations

    shu followed by ō or āng

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.13
    お店
    1.05
    D
    1.05
    L
    1.02
    い
    1.01
    お金
    0.99
    T
    0.96
     می
    0.94
    K
    0.94
    Jenis
    0.93
    POSITIVE LOGITS
    1.24
    t
    1.17
    いました
    1.16
    is
    1.13
    um
    1.13
    ات
    1.09
     tinge
    1.06
    uk
    1.04
    oy
    1.01
    ua
    1.01
    Act Density 0.000%

    No Known Activations