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

    Neuronpedia

    INDEX
    Explanations

    testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nakalista
    -1.09
    testing
    -1.07
    IUrlHelper
    -0.96
    tests
    -0.95
    +#+
    -0.91
     TextInputType
    -0.91
    ConstraintMaker
    -0.90
    ergies
    -0.84
    findpost
    -0.84
     springfox
    -0.82
    POSITIVE LOGITS
    ,
    0.60
     ad
    0.57
     as
    0.53
     is
    0.52
     (
    0.50
    .
    0.49
     and
    0.49
     with
    0.48
     for
    0.47
     o
    0.46
    Act Density 0.052%

    No Known Activations