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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accordingly
    -0.10
    .↵↵
    -0.10
    ?↵↵
    -0.09
    ?',
    -0.09
    '.↵↵
    -0.09
    。从
    -0.09
    .'↵↵
    -0.09
    。所以
    -0.08
    .');↵↵
    -0.08
    。因此
    -0.08
    POSITIVE LOGITS
     someone
    0.16
    someone
    0.15
     students
    0.15
     Someone
    0.15
     they'd
    0.15
     কেউ
    0.14
     somebody
    0.14
     negative
    0.14
     વિદ્યાર્થીઓ
    0.14
     الطلاب
    0.14
    Act Density 0.128%

    No Known Activations