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

    Neuronpedia

    INDEX
    Explanations

    movie summaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     특별
    -0.07
     평균
    -0.06
     arch
    -0.06
    _arch
    -0.06
    测试
    -0.06
    攻击
    -0.06
    mî
    -0.06
    人员
    -0.06
     дві
    -0.06
    ..."↵↵
    -0.06
    POSITIVE LOGITS
    lest
    0.06
    ńst
    0.06
    BOVE
    0.06
    Modes
    0.06
     pumpkin
    0.06
    gend
    0.06
     Lun
    0.06
    068
    0.06
     });
    0.06
    Amy
    0.06
    Act Density 0.023%

    No Known Activations