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

    Neuronpedia

    INDEX
    Explanations

    ending words like -ine, -one, -ue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     imidazol
    0.94
    imidazol
    0.88
    сибир
    0.87
    ੀਆਂ
    0.83
     ඔවුන්
    0.82
     അയാള
    0.82
     गर्
    0.81
    തിന്
    0.81
    ｃｍ
    0.79
    畋
    0.79
    POSITIVE LOGITS
    lide
    1.38
     Hale
    1.37
    wne
    1.32
    ane
    1.31
    inne
    1.31
    ike
    1.31
     Kane
    1.30
    lime
    1.30
    ixe
    1.30
    cte
    1.29
    Act Density 2.055%

    No Known Activations