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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    意向
    -0.07
    Visual
    -0.07
     %-
    -0.07
     viewHolder
    -0.07
    nings
    -0.07
    冤
    -0.07
     רפואי
    -0.06
     latino
    -0.06
    Male
    -0.06
    ().↵
    -0.06
    POSITIVE LOGITS
    袯
    0.07
    澽
    0.07
    গ
    0.07
     infect
    0.07
     Seymour
    0.07
    AIM
    0.07
    加深
    0.07
    姘
    0.06
    侮辱
    0.06
    Abort
    0.06
    Act Density 0.004%

    No Known Activations