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

    Neuronpedia

    INDEX
    Explanations

    cautionary notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     by
    1.42
    by
    1.15
     توسط
    1.10
     oleh
    0.97
    0.97
     amethyst
    0.88
     tomonidan
    0.85
     protégé
    0.84
     agreg
    0.84
    zhang
    0.83
    POSITIVE LOGITS
    il
    1.44
    ir
    1.38
    ана
    1.37
    er
    1.30
    н
    1.27
    у
    1.25
    ر
    1.24
    ب
    1.23
    m
    1.19
    ад
    1.16
    Act Density 0.005%

    No Known Activations