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

    Neuronpedia

    INDEX
    Explanations

    biological family names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    1.08
     at
    0.81
    ния
    0.79
    తో
    0.77
    }(-
    0.76
    емых
    0.75
    트를
    0.72
    ícia
    0.72
    თა
    0.71
    لے
    0.70
    POSITIVE LOGITS
    在
    1.59
    ও
    1.47
    も
    1.46
    도
    1.30
    و
    1.28
     در
    1.24
    ع
    1.20
    ו
    1.20
    out
    1.19
    もら
    1.19
    Act Density 0.000%

    No Known Activations