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

    Neuronpedia

    INDEX
    Explanations

    foreign words and scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    高
    1.02
     parten
    1.01
     Schutz
    1.00
    是一名
    0.98
     generell
    0.97
     coinvol
    0.95
    那
    0.95
     besondere
    0.95
    有限
    0.93
     Bra
    0.93
    POSITIVE LOGITS
     debtors
    1.18
     Englishmen
    1.12
    basename
    1.09
    分鐘
    1.09
     Tho
    1.08
     creditors
    1.05
     afresh
    1.01
    坫
    1.00
    ಬ್ಬಿಣ
    1.00
     Scots
    1.00
    Act Density 0.000%

    No Known Activations