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

    Neuronpedia

    INDEX
    Explanations

    create a something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Anyone
    0.89
    Any
    0.84
     meydana
    0.80
     podendo
    0.77
     Anybody
    0.76
    Anybody
    0.75
     Anyone
    0.74
     وغیرہ
    0.73
     jeweil
    0.72
     Any
    0.72
    POSITIVE LOGITS
     several
    1.93
     some
    1.62
     something
    1.61
     a
    1.55
     an
    1.53
     two
    1.52
     three
    1.47
    several
    1.33
     another
    1.30
     four
    1.28
    Act Density 4.195%

    No Known Activations