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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?>
    -0.07
    (AL
    -0.07
    (Class
    -0.06
     quar
    -0.06
    _Part
    -0.06
     mínimo
    -0.06
     ]),↵
    -0.06
     avalanche
    -0.06
    <Map
    -0.06
     INLINE
    -0.06
    POSITIVE LOGITS
    mayacak
    0.07
     sophistic
    0.06
    assed
    0.06
    -under
    0.06
     sacrificing
    0.06
     solely
    0.06
    ства
    0.06
     않을
    0.06
     Bilder
    0.06
    otine
    0.06
    Act Density 0.016%

    No Known Activations