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

    Neuronpedia

    INDEX
    Explanations

    People

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ادی
    -0.07
    861
    -0.07
     Collections
    -0.07
    mann
    -0.06
    灵
    -0.06
    .valid
    -0.06
    グラ
    -0.06
    혼
    -0.06
    ыш
    -0.06
    оги
    -0.06
    POSITIVE LOGITS
     Specifically
    0.07
    ].'
    0.06
    販
    0.06
    (Note
    0.06
    _update
    0.06
     плен
    0.06
    incare
    0.06
     церков
    0.06
    /*/
    0.05
     stalls
    0.05
    Act Density 0.023%

    No Known Activations