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

    Neuronpedia

    INDEX
    Explanations

    capital cities and districts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    বাহী
    1.49
    akat
    1.45
    𝗆
    1.43
    ക്ക്
    1.34
    estructive
    1.30
    ানের
    1.29
    rale
    1.29
    能在
    1.28
     perfused
    1.28
    𝐌
    1.27
    POSITIVE LOGITS
    ال
    1.82
    a
    1.80
    en
    1.67
    l
    1.64
    া
    1.45
    kring
    1.45
    ה
    1.39
    न
    1.38
    ⇤
    1.37
    요
    1.35
    Act Density 0.023%

    No Known Activations