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

    Neuronpedia

    INDEX
    Explanations

    LaTeX structural commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    0.56
    ل
    0.54
     nazionali
    0.53
     populer
    0.52
     deriv
    0.50
    k
    0.50
     rewritten
    0.49
    nian
    0.49
     biomark
    0.48
    ul
    0.48
    POSITIVE LOGITS
    }{
    0.71
    {
    0.59
    ется
    0.58
    ли
    0.55
     as
    0.55
     Ра
    0.54
     dürfte
    0.53
    ?)
    0.52
    َى
    0.51
    )$,
    0.51
    Act Density 0.000%

    No Known Activations