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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     theirs
    -0.07
     обеспе
    -0.06
    参数
    -0.06
    >);↵
    -0.06
     deutschland
    -0.06
    �
    -0.06
     []),↵
    -0.06
    ')),
    -0.06
     ]);
    -0.06
     fears
    -0.06
    POSITIVE LOGITS
     RX
    0.07
    anteed
    0.06
     查
    0.06
    損
    0.06
     ayr
    0.06
     �
    0.06
    AMED
    0.06
    冒
    0.06
    คอม
    0.06
    _wait
    0.06
    Act Density 0.000%

    No Known Activations