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

    Neuronpedia

    INDEX
    Explanations

    complex algorithms and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    de
    1.04
    ৯
    0.86
     continuamos
    0.85
     variedades
    0.84
     квітня
    0.84
    IÓN
    0.83
     julho
    0.81
    ဝန်
    0.79
     septiembre
    0.78
     वचन
    0.78
    POSITIVE LOGITS
    ار
    0.78
    يف
    0.74
    啲
    0.71
     cleans
    0.69
     ек
    0.68
    Ἑ
    0.68
     TPU
    0.66
    يل
    0.66
    ству
    0.66
     הד
    0.65
    Act Density 0.001%

    No Known Activations