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

    Neuronpedia

    INDEX
    Explanations

    import re

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     actually
    0.44
     răng
    0.42
     معنات
    0.40
    က်
    0.38
     biến
    0.37
     těch
    0.37
    Actually
    0.36
     فى
    0.36
     nive
    0.35
     ideales
    0.35
    POSITIVE LOGITS
    after
    0.46
     after
    0.41
     pärast
    0.39
     dopo
    0.38
     After
    0.38
     Après
    0.38
     যাহা
    0.38
     après
    0.38
     trajectories
    0.37
     arşivlendi
    0.36
    Act Density 0.000%

    No Known Activations