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

    Neuronpedia

    INDEX
    Explanations

    Parentheses/dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    预
    -0.07
    ัญญ
    -0.06
    ><?=$
    -0.06
    Shift
    -0.06
    ]?.
    -0.06
     mind
    -0.06
    )를
    -0.06
    -shop
    -0.06
    questions
    -0.06
    을
    -0.06
    POSITIVE LOGITS
     индивиду
    0.07
     وزارت
    0.06
     announced
    0.06
     Jeans
    0.06
     Cuban
    0.06
     розрахун
    0.06
     генера
    0.06
     Firmware
    0.06
    Michigan
    0.06
    forman
    0.06
    Act Density 0.024%

    No Known Activations