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

    Neuronpedia

    INDEX
    Explanations

    say "long"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Multi
    0.60
     Mult
    0.59
    Mult
    0.58
    Multi
    0.58
     Short
    0.57
    Short
    0.57
     मल्टी
    0.55
    mult
    0.53
     multi
    0.51
     mult
    0.49
    POSITIVE LOGITS
     longer
    1.60
    longer
    1.48
     طول
    1.42
     dłu
    1.37
     länger
    1.34
     panjang
    1.32
     lengthened
    1.30
     дли
    1.28
     læng
    1.28
     längre
    1.27
    Act Density 0.002%

    No Known Activations