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

    Neuronpedia

    INDEX
    Explanations

    route for paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quals
    1.51
     ilişkin
    1.26
     largura
    1.21
    ınıza
    1.21
     любых
    1.21
     torsion
    1.20
    BURTS
    1.19
     работников
    1.18
     istilah
    1.18
    ının
    1.16
    POSITIVE LOGITS
    friend
    0.97
    ع
    0.96
     سوی
    0.93
    is
    0.92
    𝙧
    0.90
    our
    0.90
    هم
    0.90
    us
    0.90
     base
    0.88
    ئی
    0.86
    Act Density 0.001%

    No Known Activations