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

    Neuronpedia

    INDEX
    Explanations

    possessive 's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Prius
    0.49
     Pikachu
    0.47
     उतर
    0.46
    ight
    0.46
     නිසා
    0.46
    ത്തിയത്
    0.45
     பேசு
    0.45
    啤
    0.45
     construire
    0.45
     tragic
    0.45
    POSITIVE LOGITS
    ני
    0.48
     -
    0.47
    z
    0.46
    рова
    0.45
    交
    0.45
     discrep
    0.45
    zf
    0.44
     تَ
    0.44
    '
    0.43
    宁
    0.43
    Act Density 0.111%

    No Known Activations