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

    Neuronpedia

    INDEX
    Explanations

    sailing and related movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    می
    1.33
    า
    1.25
    ক
    1.12
    ง
    1.11
    но
    1.09
    าย
    1.05
    ก
    1.02
    ното
    0.98
    த்தில்
    0.97
    ק
    0.96
    POSITIVE LOGITS
    l
    1.16
    cs
    0.92
    ges
    0.90
    ↵
    0.86
    the
    0.86
    cm
    0.86
    me
    0.84
    they
    0.79
    ફેદ
    0.78
    én
    0.77
    Act Density 0.001%

    No Known Activations