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

    Neuronpedia

    INDEX
    Explanations

    Q and Q-ending abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bekend
    0.40
    衣裙
    0.38
     यूपीएससी
    0.38
    ادية
    0.38
    OpportunitiesBy
    0.38
     "`
    0.37
    گنڈ
    0.37
     '|')
    0.37
    PreferenceKeys
    0.37
     थांब
    0.37
    POSITIVE LOGITS
    iqi
    0.63
    Q
    0.63
    an
    0.60
    ureshi
    0.59
     q
    0.58
     Q
    0.57
    iq
    0.56
    ul
    0.54
    eq
    0.54
    ed
    0.54
    Act Density 0.020%

    No Known Activations