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

    Neuronpedia

    INDEX
    Explanations

    understand more

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     còn
    0.86
     ainda
    0.81
    还
    0.81
    还可以
    0.77
    還可以
    0.77
     еще
    0.75
    还会
    0.75
     noch
    0.74
     todavía
    0.74
     masih
    0.73
    POSITIVE LOGITS
    了解
    0.96
     understand
    0.73
     understands
    0.66
     NOR
    0.65
    NOR
    0.64
     slightest
    0.63
     paham
    0.63
    understand
    0.62
     Understand
    0.61
    瞭
    0.61
    Act Density 0.002%

    No Known Activations