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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fasta
    -0.07
     Tory
    -0.07
     Garrison
    -0.07
    cache
    -0.07
     англ
    -0.07
    _PA
    -0.06
     Krish
    -0.06
    Pizza
    -0.06
    /activity
    -0.06
    sehen
    -0.06
    POSITIVE LOGITS
    els
    0.07
    �
    0.07
    incerely
    0.07
     cancelButton
    0.06
     #[
    0.06
     #'
    0.06
    赛
    0.06
    least
    0.06
    星
    0.06
     ((
    0.06
    Act Density 0.089%

    No Known Activations