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

    Neuronpedia

    INDEX
    Explanations

    code, computing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _io
    -0.06
    �除
    -0.06
     일본
    -0.06
    anners
    -0.06
     Urb
    -0.06
    ुह
    -0.06
     illuminate
    -0.06
     budding
    -0.06
    <Entry
    -0.06
    드로
    -0.06
    POSITIVE LOGITS
    }/${
    0.07
    ,out
    0.07
    ulu
    0.06
    [$
    0.06
    ,F
    0.06
    UnitOfWork
    0.06
     Brothers
    0.06
    ,f
    0.06
    collections
    0.06
    ):
    0.06
    Act Density 0.064%

    No Known Activations