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

    Neuronpedia

    INDEX
    Explanations

    kind or rising or fair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.60
     at
    0.49
    д
    0.46
     nymphs
    0.45
    лее
    0.42
    刄
    0.42
     of
    0.41
    мые
    0.41
     kilobytes
    0.41
     gums
    0.40
    POSITIVE LOGITS
    and
    0.59
    new
    0.55
     нынеш
    0.51
    one
    0.50
    ing
    0.50
     cinco
    0.49
    anche
    0.48
     தானே
    0.46
     عندي
    0.46
    The
    0.45
    Act Density 0.089%

    No Known Activations