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

    Neuronpedia

    INDEX
    Explanations

    _EXPORT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frem
    -0.07
     verdiği
    -0.07
    锏
    -0.07
     bulld
    -0.07
    рг
    -0.07
    してきた
    -0.06
    撐
    -0.06
     WON
    -0.06
     smarter
    -0.06
    营造
    -0.06
    POSITIVE LOGITS
    礼貌
    0.08
    物业
    0.07
    lical
    0.07
    (sequence
    0.07
    ocese
    0.07
    mente
    0.07
    𬶟
    0.07
    vi
    0.07
    具体内容
    0.07
     pena
    0.07
    Act Density 0.001%

    No Known Activations