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

    Neuronpedia

    INDEX
    Explanations

    not X but Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     যাওয়ার
    0.41
     sedangkan
    0.39
     natomiast
    0.38
    sthe
    0.37
    ществует
    0.36
    beyond
    0.36
    T
    0.36
    niejsze
    0.35
    istem
    0.35
     இந்நிலையில்
    0.34
    POSITIVE LOGITS
     sondern
    0.77
     but
    0.73
     बल्कि
    0.70
    而是
    0.63
     nhưng
    0.61
     αλλά
    0.53
     hanem
    0.53
     mutta
    0.52
     sino
    0.50
    แต่
    0.50
    Act Density 0.113%

    No Known Activations