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

    Neuronpedia

    INDEX
    Explanations

    need to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strument
    0.44
     third
    0.43
     fratello
    0.43
     جد
    0.43
     tập
    0.42
     konstru
    0.42
     nam
    0.42
     üld
    0.42
     junt
    0.41
     quirúrg
    0.41
    POSITIVE LOGITS
    waved
    0.49
    oauth
    0.47
    tuning
    0.47
     ಅವರು
    0.47
    nên
    0.47
    所以
    0.46
    लेकिन
    0.44
    rapers
    0.43
     Rosemary
    0.43
    ციის
    0.43
    Act Density 0.004%

    No Known Activations