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

    Neuronpedia

    INDEX
    Explanations

    adaptive thresholding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trống
    0.43
    billy
    0.38
     হলাম
    0.38
     еще
    0.37
     valleys
    0.37
     metre
    0.37
    ৮
    0.36
     চূড়ান্ত
    0.36
    最高
    0.36
    Glu
    0.36
    POSITIVE LOGITS
     ნაკ
    0.43
    Minimize
    0.41
     oprac
    0.41
    Makes
    0.39
     Makes
    0.38
     Minimize
    0.38
    াভাব
    0.38
    変わ
    0.38
    Rafael
    0.38
     Somewhat
    0.37
    Act Density 0.001%

    No Known Activations