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

    Neuronpedia

    INDEX
    Explanations

    country names in persian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mlijeka
    1.33
     børn
    1.26
     precludes
    1.20
    𝐪
    1.17
     blemishes
    1.16
     scrollBody
    1.15
     byen
    1.14
     mennes
    1.13
     ditches
    1.13
     scathing
    1.13
    POSITIVE LOGITS
     در
    1.56
     به
    1.52
     با
    1.38
     از
    1.38
     و
    1.34
     پ
    1.27
     این
    1.27
    پ
    1.27
     است
    1.26
     د
    1.25
    Act Density 0.002%

    No Known Activations