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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Taj
    -0.27
     Regel
    -0.27
    illard
    -0.27
    满èĦ¸
    -0.25
     concess
    -0.25
    ulp
    -0.25
    [np
    -0.25
    [right
    -0.25
    ijo
    -0.24
    æĬĢæľ¯äººåijĺ
    -0.24
    POSITIVE LOGITS
     sustain
    0.27
     orient
    0.26
     sustaining
    0.26
    伦
    0.26
    ç»´
    0.26
    奴
    0.25
    cate
    0.25
    AAC
    0.25
    翼
    0.25
     resets
    0.25
    Act Density 4.117%

    No Known Activations