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

    Neuronpedia

    INDEX
    Explanations

    Nanjing University

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    1.49
    s
    1.27
    TI
    1.20
    ED
    1.18
    Equations
    1.14
    he
    1.13
    all
    1.11
    GL
    1.11
    SO
    1.10
    and
    1.09
    POSITIVE LOGITS
    ى
    1.13
    리로
    1.09
    า
    1.05
    ி
    0.98
    يته
    0.98
    ний
    0.96
    ması
    0.96
    л
    0.95
     t
    0.93
     sassy
    0.93
    Act Density 0.000%

    No Known Activations