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

    Neuronpedia

    INDEX
    Explanations

    fibonacci arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ０
    0.98
     حوالي
    0.93
     ۲۰۰
    0.91
     डेढ़
    0.90
     ಸಾವಿರ
    0.89
     ২০
    0.88
     тысяч
    0.87
     ಸುಮ
    0.87
     około
    0.86
     eighty
    0.86
    POSITIVE LOGITS
    <b>
    0.46
     me
    0.43
    め
    0.43
     Buddhists
    0.38
     se
    0.38
     blur
    0.38
     Belief
    0.38
     Rabbit
    0.37
     staking
    0.37
     en
    0.37
    Act Density 0.223%

    No Known Activations