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

    Neuronpedia

    INDEX
    Explanations

    words ending in "-ility"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    1.24
    も
    1.20
    EN
    1.12
    도
    1.06
    q
    1.02
    ER
    1.02
    l
    1.00
    に使
    0.97
    ENT
    0.97
     меня
    0.96
    POSITIVE LOGITS
    ur
    1.30
     for
    1.29
    ات
    1.22
    ről
    1.18
    ي
    1.14
    يس
    1.09
    وم
    1.06
    ولي
    1.05
    ча
    1.05
     arrêter
    1.02
    Act Density 0.001%

    No Known Activations