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

    Neuronpedia

    INDEX
    Explanations

    given

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ptron
    -0.07
    ў
    -0.07
    lect
    -0.06
    िध
    -0.06
    魔法
    -0.06
    Keep
    -0.06
    onaut
    -0.06
    &oacute
    -0.06
    uctions
    -0.06
    数量
    -0.06
    POSITIVE LOGITS
    Electronic
    0.08
     Schwe
    0.07
     связ
    0.07
     Marion
    0.06
     Kerr
    0.06
    ()])↵
    0.06
     electronic
    0.06
     diese
    0.06
     Favorite
    0.06
     WoW
    0.06
    Act Density 0.012%

    No Known Activations