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

    Neuronpedia

    INDEX
    Explanations

    crashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irection
    -0.07
     Teil
    -0.07
     confidential
    -0.07
    iveau
    -0.07
    引入
    -0.07
     fullfile
    -0.06
     adolescence
    -0.06
     아이
    -0.06
    户籍
    -0.06
    发起
    -0.06
    POSITIVE LOGITS
    영상
    0.07
     Busty
    0.07
     económ
    0.07
     elevated
    0.07
     Procedure
    0.07
     Pens
    0.07
     Political
    0.07
    واق
    0.07
     anterior
    0.06
     continental
    0.06
    Act Density 0.004%

    No Known Activations