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

    Neuronpedia

    INDEX
    Explanations

    is a type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जिससे
    0.33
     the
    0.32
    ".
    0.32
     sepen
    0.29
    ก่อน
    0.29
     чтобы
    0.29
     ताकि
    0.29
     before
    0.28
     against
    0.28
    before
    0.28
    POSITIVE LOGITS
     consists
    0.70
     είναι
    0.69
    是一种
    0.67
    是一個
    0.66
     является
    0.64
    是一个
    0.63
     comprises
    0.63
     provides
    0.61
     adalah
    0.61
     encompasses
    0.60
    Act Density 0.214%

    No Known Activations