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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /rand
    -0.07
    етерб
    -0.06
    _was
    -0.06
    논
    -0.06
    berapa
    -0.06
     tonumber
    -0.06
     scanners
    -0.06
     nord
    -0.06
    들은
    -0.06
     AFP
    -0.06
    POSITIVE LOGITS
     Exercises
    0.07
    (fill
    0.07
    ое
    0.07
    ,sum
    0.06
    endimento
    0.06
    -sur
    0.06
    的一
    0.06
     �
    0.06
    :b
    0.06
     sur
    0.06
    Act Density 0.012%

    No Known Activations