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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whom
    -0.07
     endowed
    -0.07
    Th
    -0.06
    Precision
    -0.06
    东省
    -0.06
    飛
    -0.06
    テル
    -0.06
     Gros
    -0.06
    .removeClass
    -0.06
     lest
    -0.06
    POSITIVE LOGITS
    　j
    0.07
     ",
    0.07
    >-
    0.07
     Jaime
    0.06
     />;↵
    0.06
     RTP
    0.06
    اعدة
    0.06
    }')↵
    0.06
     "{$
    0.06
     عند
    0.06
    Act Density 0.039%

    No Known Activations