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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    576
    -0.07
    álních
    -0.07
    匹
    -0.06
    trap
    -0.06
    โ
    -0.06
    _tracks
    -0.06
     incidental
    -0.06
    _amp
    -0.06
    �
    -0.06
     rivalry
    -0.06
    POSITIVE LOGITS
    _DENIED
    0.07
     skeleton
    0.06
    /Test
    0.06
    되고
    0.06
    (down
    0.06
    (question
    0.06
    ALL
    0.06
     Chance
    0.06
     skeletons
    0.06
    (reordered
    0.06
    Act Density 0.002%

    No Known Activations