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

    Neuronpedia

    INDEX
    Explanations

    scenic routes and views

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     with
    1.03
     or
    0.98
    es
    0.91
    t
    0.90
    ق
    0.86
    et
    0.83
    an
    0.83
     in
    0.82
     and
    0.82
    ون
    0.79
    POSITIVE LOGITS
    ມັນ
    0.77
    (
    0.75
    전히
    0.72
    ྕ
    0.68
    3
    0.67
    доо
    0.65
    4
    0.65
     dices
    0.65
    5
    0.63
    ४
    0.63
    Act Density 0.002%

    No Known Activations