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

    Neuronpedia

    INDEX
    Explanations

    Western feel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     推
    0.42
     मिश्रण
    0.40
     summa
    0.39
     titre
    0.39
     сумму
    0.39
     والن
    0.38
    esome
    0.37
     pamoja
    0.37
     فروغ
    0.37
     箱
    0.37
    POSITIVE LOGITS
    bookmarks
    0.40
    construct
    0.38
    detect
    0.38
    powers
    0.37
     Frederic
    0.37
    იშ
    0.37
    find
    0.36
     DeL
    0.36
     ability
    0.36
    Chand
    0.35
    Act Density 0.000%

    No Known Activations