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

    Neuronpedia

    INDEX
    Explanations

    Power lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     Recap
    -0.07
    ﰜ
    -0.06
     Psy
    -0.06
    peare
    -0.06
    촣
    -0.06
    aze
    -0.06
    andin
    -0.06
     Bravo
    -0.06
    _seek
    -0.06
    POSITIVE LOGITS
    姚
    0.08
    _lot
    0.08
    Women
    0.08
    泡
    0.07
    مور
    0.07
    摇滚
    0.07
    男士
    0.07
     kị
    0.07
    臟
    0.07
    stanbul
    0.07
    Act Density 0.011%

    No Known Activations