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

    Neuronpedia

    INDEX
    Explanations

    provides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nebude
    0.44
     đừng
    0.44
     neće
    0.42
     нюан
    0.41
     måtte
    0.41
     Gefühl
    0.41
     ними
    0.40
     отметил
    0.40
    പക്ഷ
    0.40
     evitar
    0.40
    POSITIVE LOGITS
     provides
    0.73
     provide
    0.63
    provides
    0.63
     providing
    0.58
     Provides
    0.58
    Provides
    0.55
     combines
    0.53
     delivers
    0.52
     creates
    0.51
    provide
    0.50
    Act Density 0.541%

    No Known Activations