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

    Neuronpedia

    INDEX
    Explanations

    connecting items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     etc
    0.77
    etc
    0.75
     ইত্যাদি
    0.60
     Etc
    0.59
    甚至
    0.59
     आदि
    0.57
     or
    0.57
     тощо
    0.56
     nejen
    0.56
     или
    0.54
    POSITIVE LOGITS
     secondly
    0.63
     zároveň
    0.60
     another
    0.55
    rogens
    0.52
     separately
    0.51
     отдельно
    0.51
    ंगाबाद
    0.50
     its
    0.48
     lastly
    0.48
     various
    0.47
    Act Density 0.121%

    No Known Activations