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

    Neuronpedia

    INDEX
    Explanations

    yes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unfairly
    -0.08
    ially
    -0.07
     norge
    -0.07
     hygiene
    -0.07
    jenis
    -0.07
    idal
    -0.07
    ước
    -0.06
    Months
    -0.06
    cod
    -0.06
     offshore
    -0.06
    POSITIVE LOGITS
     Tất
    0.07
    ?>">↵
    0.07
     Schools
    0.07
    Intel
    0.07
    珍惜
    0.07
    狳
    0.07
    _env
    0.07
     luk
    0.07
     gst
    0.07
    parents
    0.07
    Act Density 0.028%

    No Known Activations