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

    Neuronpedia

    INDEX
    Explanations

    a "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وغيرها
    0.63
     сложных
    0.59
    เหล่านี้
    0.54
     비슷
    0.52
     जिनसे
    0.52
     بمعنى
    0.51
     وه
    0.50
     كلها
    0.50
     خلينا
    0.49
     분야
    0.49
    POSITIVE LOGITS
     the
    1.17
     an
    0.90
     thisobject
    0.84
     a
    0.82
     ihe
    0.81
    the
    0.79
     one
    0.78
     thei
    0.78
    <unused2197>
    0.74
     teh
    0.73
    Act Density 5.130%

    No Known Activations