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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     for
    -0.07
    >
    -0.07
    (schedule
    -0.07
    (?
    -0.06
     contests
    -0.06
    -for
    -0.06
    ",↵
    -0.06
    zburg
    -0.06
    [frame
    -0.06
     acknowled
    -0.06
    POSITIVE LOGITS
    .IsChecked
    0.06
     Ф
    0.06
     Bez
    0.06
     interle
    0.06
    sess
    0.06
    徳
    0.06
     ألف
    0.06
    ?]
    0.06
    ायल
    0.06
    esis
    0.06
    Act Density 0.030%

    No Known Activations