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

    Neuronpedia

    INDEX
    Explanations

    fixed income investments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    2.20
    ת
    2.14
    ন
    1.80
    ק
    1.77
    א
    1.70
    ב
    1.66
    ज
    1.66
    ن
    1.63
    ী
    1.63
    ট
    1.59
    POSITIVE LOGITS
     αυτό
    1.14
    ání
    1.09
    have
    1.02
    the
    0.98
    0.95
     és
    0.93
    ↵
    0.90
    ного
    0.86
     potência
    0.86
    ình
    0.85
    Act Density 0.000%

    No Known Activations