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

    Neuronpedia

    INDEX
    Explanations

    at least

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cleverly
    0.52
     gând
    0.52
     rápidamente
    0.50
     ممكن
    0.47
    どんどん
    0.47
     bardziej
    0.45
     eril
    0.45
    很快
    0.44
     möglichen
    0.44
     possibile
    0.44
    POSITIVE LOGITS
    至少
    1.44
     almeno
    1.28
     কমপক্ষে
    1.28
    少なくとも
    1.25
     mindestens
    1.19
     atleast
    1.16
     ≥
    0.96
    ≥
    0.93
     অন্তত
    0.92
     حداقل
    0.91
    Act Density 0.052%

    No Known Activations