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

    Neuronpedia

    INDEX
    Explanations

    first-class cricketer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ื้อ
    -0.79
    '.$
    -0.75
    ==$
    -0.74
    uscular
    -0.73
    ofo
    -0.71
    تمع
    -0.71
    "](
    -0.71
    malink
    -0.70
    ]()
    -0.69
    resultado
    -0.69
    POSITIVE LOGITS
     international
    1.99
    international
    1.67
     Test
    1.66
     county
    1.63
     domestic
    1.48
     test
    1.40
     internationalen
    1.39
     TEST
    1.38
    Test
    1.36
     международ
    1.34
    Act Density 0.077%

    No Known Activations