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

    Neuronpedia

    INDEX
    Explanations

    not simply X; instead Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ),"
    0.45
     হওয়ায়
    0.43
    ?"
    0.42
    )"
    0.42
    仍
    0.42
     both
    0.42
     হওয়ায়
    0.41
     Và
    0.40
     ไง
    0.40
    ไง
    0.40
    POSITIVE LOGITS
    而是
    1.18
     बल्कि
    1.14
     بلکه
    1.07
     sondern
    1.06
    ;
    1.05
     hanem
    1.04
    ؛
    0.95
     بلکہ
    0.93
     sino
    0.83
    ；
    0.82
    Act Density 0.035%

    No Known Activations