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

    Neuronpedia

    INDEX
    Explanations

    distort, affect, and offset

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    促进
    0.43
    凝聚
    0.42
     facilitation
    0.42
     fomentar
    0.41
     coincid
    0.41
     फेस्टिवल
    0.40
    পল
    0.40
     aislamiento
    0.40
     combustível
    0.40
     પસંદ
    0.40
    POSITIVE LOGITS
     complicates
    1.01
     complicating
    0.94
     complicate
    0.93
     complication
    0.82
     confound
    0.75
     distort
    0.71
     modify
    0.70
     complications
    0.70
     modifies
    0.70
     komplik
    0.68
    Act Density 0.031%

    No Known Activations