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

    Neuronpedia

    INDEX
    Explanations

    explaining complex topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অথবা
    0.24
     లేదా
    0.24
     அல்லது
    0.22
     veya
    0.22
     ឬ
    0.22
     अथवा
    0.22
     أو
    0.22
    のではなく
    0.21
    或者是
    0.20
     또는
    0.20
    POSITIVE LOGITS
     особенно
    0.28
    尤其是
    0.27
     especially
    0.27
    !
    0.27
    因为它
    0.26
    ！
    0.24
    especially
    0.24
     soprattutto
    0.24
     благодаря
    0.24
     enough
    0.24
    Act Density 0.823%

    No Known Activations