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

    Neuronpedia

    INDEX
    Explanations

    URL path routing `startswith`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     *}
    0.50
     *:
    0.44
     **,
    0.44
    iams
    0.43
     curviliné
    0.43
     *"
    0.38
     *,
    0.37
    **,
    0.37
     '*',
    0.36
    }^{*}
    0.36
    POSITIVE LOGITS
    $[
    0.41
    ([-
    0.40
    DAR
    0.40
    Sheet
    0.38
     [#
    0.38
    _{[
    0.37
     sheet
    0.36
    Suggest
    0.36
    SDL
    0.34
    {[
    0.34
    Act Density 0.002%

    No Known Activations