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

    Neuronpedia

    INDEX
    Explanations

    a/an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     since
    0.35
     seus
    0.33
     as
    0.32
     entrambi
    0.31
    க்கு
    0.31
     dey
    0.31
     অর্থে
    0.31
     spp
    0.30
    ış
    0.30
     থাকলে
    0.30
    POSITIVE LOGITS
     một
    0.90
     sebuah
    0.89
     isang
    0.85
     një
    0.85
     ένα
    0.82
     einem
    0.82
     একটি
    0.80
    một
    0.78
     एक
    0.75
     μια
    0.75
    Act Density 0.232%

    No Known Activations