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

    Neuronpedia

    INDEX
    Explanations

    sentence endings followed by 'Our' or 'The'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，“
    0.28
     guardar
    0.25
    ，
    0.24
    '
    0.24
    0.23
     weet
    0.23
     calcule
    0.21
    ”，“
    0.21
    ếu
    0.21
    方程
    0.21
    POSITIVE LOGITS
    in
    0.30
    Y
    0.28
     in
    0.27
    1
    0.26
    도
    0.25
    H
    0.24
    ید
    0.22
     intelligents
    0.22
    im
    0.22
    이기
    0.22
    Act Density 0.000%

    No Known Activations