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

    Neuronpedia

    INDEX
    Explanations

    io. or io/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    1.07
    ми
    0.99
    i
    0.98
    inah
    0.97
    ри
    0.92
    ीय
    0.91
    ಿಗಳು
    0.91
    innt
    0.91
     in
    0.90
    iiv
    0.90
    POSITIVE LOGITS
    ك
    1.37
     that
    1.35
    io
    1.20
     que
    1.11
    のは
    1.04
     THAT
    0.93
    that
    0.91
     בי
    0.89
    ка
    0.89
    R
    0.87
    Act Density 0.004%

    No Known Activations