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

    Neuronpedia

    INDEX
    Explanations

    but rather

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     علاوہ
    0.46
     বলেও
    0.42
    }+$
    0.38
     Và
    0.37
     lc
    0.37
     Gets
    0.36
    ∵
    0.36
     só
    0.35
     breath
    0.35
     ds
    0.35
    POSITIVE LOGITS
    而是
    1.01
     बल्कि
    0.95
     rather
    0.95
     بلکه
    0.92
     скорее
    0.87
     بلکہ
    0.83
    rather
    0.83
     বরং
    0.82
    Rather
    0.78
     sondern
    0.77
    Act Density 0.019%

    No Known Activations