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

    Neuronpedia

    INDEX
    Explanations

    greater than or equal to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    િય
    0.39
     चुप
    0.37
     થો
    0.37
    边的
    0.35
     झ
    0.35
    လိုက်
    0.35
    ਼
    0.34
    డంలో
    0.34
    uttosto
    0.34
    란드
    0.34
    POSITIVE LOGITS
     >=
    1.86
     ≥
    1.66
    超过
    1.64
    >=
    1.58
     (>
    1.58
     $>
    1.56
    ≥
    1.53
    大于
    1.52
     beyond
    1.46
     >
    1.44
    Act Density 0.110%

    No Known Activations