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

    Neuronpedia

    INDEX
    Explanations

    concerto

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     criter
    -0.07
    :");
↵
    -0.07
     rizik
    -0.07
    цит
    -0.07
    …↵↵↵↵
    -0.07
    عية
    -0.06
    لمات
    -0.06
    ?>↵↵↵
    -0.06
     صفحه
    -0.06
     Влади
    -0.06
    POSITIVE LOGITS
    StringRef
    0.06
    sand
    0.06
    _softc
    0.06
    -bodied
    0.06
     turnovers
    0.06
     beginner
    0.06
     orange
    0.06
    _changes
    0.06
    ailed
    0.06
    ayette
    0.06
    Act Density 0.002%

    No Known Activations