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

    Neuronpedia

    INDEX
    Explanations

    November 3,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दिनांक
    0.95
     giugno
    0.94
     iunie
    0.92
    ଟି
    0.90
    derdag
    0.89
     Expires
    0.87
     август
    0.85
     calendario
    0.85
     注意
    0.84
     silam
    0.84
    POSITIVE LOGITS
     be
    0.71
     nap
    0.67
     ill
    0.67
     id
    0.66
     desire
    0.65
     fig
    0.65
     natural
    0.64
     ত্রিপ
    0.63
     phil
    0.62
     ang
    0.61
    Act Density 0.030%

    No Known Activations