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

    Neuronpedia

    INDEX
    Explanations

    sentence starters or consequentials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     naudoj
    0.80
    埌
    0.78
     digunakan
    0.77
     obter
    0.77
    📃
    0.76
     uygun
    0.76
     ഉപയോഗ
    0.76
     limpar
    0.75
     usar
    0.75
     duração
    0.75
    POSITIVE LOGITS
     This
    0.96
     Needless
    0.96
     That
    0.96
     Having
    0.93
     Quite
    0.92
    That
    0.91
     Despite
    0.91
    This
    0.90
     Frankly
    0.90
     Admittedly
    0.89
    Act Density 0.805%

    No Known Activations