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

    Neuronpedia

    INDEX
    Explanations

    lobby

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Input
    -0.08
    赛
    -0.07
     Mat
    -0.07
    .",↵
    -0.07
    Math
    -0.07
     {↵↵
    -0.07
    /resource
    -0.07
    SIZE
    -0.06
    nd
    -0.06
     uf
    -0.06
    POSITIVE LOGITS
     lobbying
    0.08
     Lobby
    0.07
     lobby
    0.07
    伊斯兰
    0.07
     הפ
    0.07
    �
    0.07
    众多
    0.07
    ————————
    0.07
     negotiated
    0.07
    翩
    0.07
    Act Density 0.002%

    No Known Activations