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

    Neuronpedia

    INDEX
    Explanations

    shell commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ဆို
    0.91
     lspace
    0.88
     डिपॉ
    0.88
     compuesta
    0.87
     کمان
    0.87
     الساعه
    0.86
     Compos
    0.86
    첨
    0.85
    seudo
    0.85
     कंप्लीट
    0.84
    POSITIVE LOGITS
    ijan
    0.77
     cut
    0.70
     tail
    0.60
     marketing
    0.59
     tr
    0.58
     In
    0.58
     Tr
    0.57
     head
    0.57
     ahead
    0.57
     while
    0.56
    Act Density 0.034%

    No Known Activations