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

    Neuronpedia

    INDEX
    Explanations

    what something is called

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     („
    0.61
     (=
    0.59
     («
    0.56
     (\"
    0.51
    SOME
    0.51
     (“
    0.48
    (=
    0.47
     (!)
    0.43
     (‘
    0.42
    独自
    0.41
    POSITIVE LOGITS
     variously
    0.80
     "
    0.71
     communément
    0.66
     either
    0.63
     simply
    0.62
     called
    0.59
     просто
    0.59
     "(
    0.57
     ‘
    0.57
     “
    0.55
    Act Density 0.256%

    No Known Activations