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

    Neuronpedia

    INDEX
    Explanations

    exceeds, greater than, below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mixte
    0.69
     നിന്ന
    0.68
     смотря
    0.68
     אמ
    0.66
     잠깐
    0.63
     hoops
    0.63
     vaikka
    0.63
     смотре
    0.62
    heses
    0.61
    лго
    0.60
    POSITIVE LOGITS
     >=
    2.47
     ≥
    2.47
    超过
    2.36
     exceeding
    2.29
     beyond
    2.29
    大于
    2.27
     exceeds
    2.18
    ≥
    2.13
    小于
    2.13
     exceed
    2.12
    Act Density 0.343%

    No Known Activations