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

    Neuronpedia

    INDEX
    Explanations

    variable definitions and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     its
    -1.39
    因为它
    -1.16
     davis
    -1.15
    "
    -1.15
     mouseY
    -1.13
    它的
    -1.10
    ínica
    -1.09
     它
    -1.09
    也是
    -1.08
    它
    -1.08
    POSITIVE LOGITS
     and
    1.72
     their
    1.35
    そして
    1.13
     etc
    1.09
     لهم
    1.08
     그리고
    1.07
     leurs
    1.07
    etc
    1.00
    中には
    1.00
     jejich
    0.96
    Act Density 0.024%

    No Known Activations