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

    Neuronpedia

    INDEX
    Explanations

    lists of activities or subjects

    np_acts-logits-general · gemini-2.5-flash-lite

    design, develop, build, sell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.73
     \
    0.71
    वर्ती
    0.58
    ummy
    0.57
    ।
    0.57
     گی۔
    0.57
    '$,
    0.56
    。
    0.56
     छोटी
    0.55
    ารย์
    0.55
    POSITIVE LOGITS
    했지만
    0.69
    DAAR
    0.67
    б
    0.64
    ak
    0.63
    o
    0.63
    u
    0.63
    на
    0.62
    d
    0.62
    н
    0.61
    しますが
    0.61
    Act Density 0.033%

    No Known Activations