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

    Neuronpedia

    INDEX
    Explanations

    veteran, slave, pirate, trainee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    1.68
    ب
    1.38
    as
    1.30
    ك
    1.30
    ing
    1.27
    al
    1.24
    ش
    1.21
    it
    1.20
    the
    1.17
    માં
    1.14
    POSITIVE LOGITS
     சிலர்
    0.85
    ENT
    0.83
    ri
    0.82
    ς
    0.79
    ៤
    0.76
     Welding
    0.76
    ៩
    0.76
    spectra
    0.75
    ನನ್ನು
    0.75
    sı
    0.75
    Act Density 0.122%

    No Known Activations