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

    Neuronpedia

    INDEX
    Explanations

    Southern Poverty Law Center

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    1.49
    of
    1.38
    ش
    1.28
     (
    1.20
    ü
    1.19
     is
    1.17
    to
    1.16
    전
    1.16
     has
    1.15
    리
    1.14
    POSITIVE LOGITS
    ’
    0.98
    :”
    0.96
    :
    0.87
     شرطونه
    0.78
    дора
    0.78
    ς
    0.77
    ])));
    0.76
    تين
    0.76
    MiddleLine
    0.75
    вою
    0.75
    Act Density 0.001%

    No Known Activations