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

    Neuronpedia

    INDEX
    Explanations

    URLs and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     】,
    0.44
     —,
    0.41
     **,
    0.39
    。",
    0.39
     '-',
    0.39
    INTa
    0.39
     ሂደት
    0.38
    𒁲
    0.38
     °,
    0.38
    <unused407>
    0.37
    POSITIVE LOGITS
    /
    1.84
    /[
    1.48
    /{
    1.47
    /.
    1.43
    /(
    1.39
    /,
    1.34
    /_
    1.32
    /)
    1.31
    /${
    1.29
    /%
    1.29
    Act Density 0.120%

    No Known Activations