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

    Neuronpedia

    INDEX
    Explanations

    url paths and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ***
    0.78
     \*
    0.76
     **
    0.72
     former
    0.69
     +,
    0.69
     *,
    0.68
     monol
    0.67
     *
    0.67
     ܀
    0.66
     dimensions
    0.65
    POSITIVE LOGITS
    /
    3.16
    /)
    2.44
    /?
    2.37
    /{
    2.33
    /,
    2.32
    /(
    2.31
    /.
    2.27
    /"
    2.24
    /_
    2.19
    /).
    2.19
    Act Density 0.652%

    No Known Activations