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

    Neuronpedia

    INDEX
    Explanations

    or synonyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dont
    0.19
     for
    0.19
     as
    0.19
     because
    0.19
    .
    0.18
     which
    0.18
    0.18
     Which
    0.18
     when
    0.18
     I
    0.18
    POSITIVE LOGITS
     guérison
    0.18
     denominators
    0.18
    ங்கும்
    0.17
     timepiece
    0.16
    kfollowers
    0.16
    襁
    0.16
    <unused82>
    0.16
     ಅಪಾಯ
    0.16
    絠
    0.16
     secretions
    0.16
    Act Density 0.000%

    No Known Activations