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
     Nä
    -0.08
     lokale
    -0.07
     Connecticut
    -0.07
    Finite
    -0.07
     Kö
    -0.07
     TEMPLATE
    -0.06
    (utils
    -0.06
     schle
    -0.06
    ibling
    -0.06
    cin
    -0.06
    POSITIVE LOGITS
     illustrated
    0.06
    умент
    0.06
    alt
    0.06
     Camping
    0.06
    adians
    0.06
    ipation
    0.06
    _article
    0.06
    Training
    0.06
     işte
    0.06
     терап
    0.06
    Act Density 0.016%

    No Known Activations