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

    Neuronpedia

    INDEX
    Explanations

    notes fade, of two, sandwich -, SC ADA, тран сля

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тся
    1.18
    inę
    1.05
    in
    1.03
     for
    1.03
     insolvent
    0.98
    {
    0.97
     congratulated
    0.96
     comprende
    0.95
     ary
    0.94
    ).
    0.92
    POSITIVE LOGITS
    on
    2.08
    ah
    1.26
    .
    1.19
    and
    1.13
    av
    1.09
    Ф
    1.08
    أ
    1.07
    도
    1.05
    ب
    1.03
    C
    1.02
    Act Density 0.000%

    No Known Activations