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

    Neuronpedia

    INDEX
    Explanations

    words ending in 'l' followed by specific suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ा
    0.74
    e
    0.72
    ece
    0.71
    eer
    0.71
    aue
    0.68
    日语
    0.66
     prized
    0.65
    ी
    0.65
     unlimited
    0.64
    ரியா
    0.64
    POSITIVE LOGITS
    led
    1.73
    lett
    1.61
    ley
    1.47
    lets
    1.47
    ล์
    1.45
    let
    1.40
    LED
    1.38
    lette
    1.37
    leys
    1.26
    lettes
    1.25
    Act Density 0.115%

    No Known Activations