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

    Neuronpedia

    INDEX
    Explanations

    one/1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ucked
    -0.07
     vô
    -0.07
    ết
    -0.07
     mem
    -0.07
     shot
    -0.06
     sagte
    -0.06
    絲
    -0.06
     read
    -0.06
    今回
    -0.06
     Answer
    -0.06
    POSITIVE LOGITS
    囟
    0.09
     Flat
    0.08
     ilişki
    0.08
    有问题
    0.07
     impairment
    0.07
    kowski
    0.07
    _person
    0.07
    东营
    0.07
    붕
    0.07
    _ORDER
    0.07
    Act Density 0.020%

    No Known Activations