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

    Neuronpedia

    INDEX
    Explanations

    defining attention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wegen
    0.41
    vrage
    0.41
     cuello
    0.39
     kanamycin
    0.39
     ligero
    0.39
     extrémités
    0.39
     Hol
    0.38
    ATUS
    0.38
     réduite
    0.38
     sif
    0.38
    POSITIVE LOGITS
    🫶
    0.47
    cole
    0.44
    Whats
    0.41
     whats
    0.41
    кол
    0.41
    NewCollection
    0.41
    Thats
    0.40
     میتوان
    0.39
     discovery
    0.38
     discovered
    0.38
    Act Density 0.000%

    No Known Activations