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

    Neuronpedia

    INDEX
    Explanations

    modern today

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     drawback
    0.41
     कच
    0.41
     নতুন
    0.40
     unprocessed
    0.39
     Ral
    0.39
     Straw
    0.38
     Boul
    0.38
     automatically
    0.37
     sh
    0.36
     Δεν
    0.36
    POSITIVE LOGITS
     нынеш
    0.81
     huidige
    0.77
    現在の
    0.71
    如今
    0.69
    现在的
    0.68
     today
    0.66
     сегодняш
    0.66
    今天的
    0.65
    現在
    0.64
     지금
    0.64
    Act Density 0.067%

    No Known Activations