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

    Neuronpedia

    INDEX
    Explanations

    catch exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ܂
    0.55
    ん
    0.52
    га
    0.51
    مكن
    0.50
    но
    0.49
    ἲ
    0.48
     комі
    0.48
    Harvey
    0.47
    ándolo
    0.47
     nuestros
    0.46
    POSITIVE LOGITS
    (
    0.57
     of
    0.49
    ของ
    0.48
     (
    0.45
    (&
    0.43
     Of
    0.43
     is
    0.42
    ('
    0.41
    }/>
    0.41
    ‘
    0.41
    Act Density 0.008%

    No Known Activations