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

    Neuronpedia

    INDEX
    Explanations

    period of, job she, world of, drink with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ।
    1.29
    。
    1.26
     والذي
    1.21
    .
    1.19
    ™.
    1.12
    ().
    1.10
    ،
    1.00
     والتي
    0.99
    .**
    0.99
    ®.
    0.99
    POSITIVE LOGITS
     both
    0.83
     colder
    0.75
    neither
    0.74
     neither
    0.72
     proportional
    0.69
     either
    0.69
     Equality
    0.68
    iciency
    0.66
    ولت
    0.66
    álne
    0.66
    Act Density 0.391%

    No Known Activations