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

    Neuronpedia

    INDEX
    Explanations

    self improvement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trai
    -0.07
     nice
    -0.06
    (propertyName
    -0.06
     thereof
    -0.06
    ‌کنندگان
    -0.06
    sahuje
    -0.06
     two
    -0.06
     six
    -0.06
     RA
    -0.06
     vested
    -0.06
    POSITIVE LOGITS
     keyst
    0.07
    采
    0.07
    'email
    0.07
    ’util
    0.07
    ETIME
    0.07
     unset
    0.06
     elem
    0.06
    ,lat
    0.06
    $(".
    0.06
    ”;
    0.06
    Act Density 0.066%

    No Known Activations