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

    Neuronpedia

    INDEX
    Explanations

    Quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Elk
    -0.07
    ielding
    -0.06
     За
    -0.06
     �
    -0.06
    Std
    -0.06
    …↵↵↵↵
    -0.06
    ertoire
    -0.06
    ças
    -0.06
    277
    -0.06
    ListModel
    -0.06
    POSITIVE LOGITS
     spaceship
    0.08
    ateurs
    0.07
     logging
    0.07
    _MAIN
    0.06
     ***↵
    0.06
    rai
    0.06
     richt
    0.06
    sanız
    0.06
    _dates
    0.06
     figsize
    0.06
    Act Density 0.002%

    No Known Activations