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

    Neuronpedia

    INDEX
    Explanations

    might like or love

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    あくまで
    0.44
     පමණ
    0.44
     모든
    0.43
     ದು
    0.43
    ኗ
    0.43
     மட்டுமே
    0.43
     obstacles
    0.41
     aseg
    0.41
    ចប់
    0.41
    ihal
    0.41
    POSITIVE LOGITS
     similar
    0.60
     interes
    0.56
     intéress
    0.55
     interest
    0.55
     좋아
    0.54
     liking
    0.54
     비슷한
    0.53
     interess
    0.52
    喜歡
    0.52
    喜欢
    0.52
    Act Density 0.027%

    No Known Activations