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

    Neuronpedia

    INDEX
    Explanations

    visual descriptions and expansion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ванням
    0.52
    innov
    0.48
     milliard
    0.47
    㷌
    0.47
     ক্লিক
    0.47
    𐰃
    0.46
    𝟯
    0.46
    was
    0.46
    Ｘ
    0.45
     munitions
    0.45
    POSITIVE LOGITS
    칙
    0.47
     EVEN
    0.43
     palabra
    0.42
    显得
    0.42
    /
    0.41
     TextInputLayout
    0.41
     kuitenkin
    0.40
     aquellos
    0.40
     PropTypes
    0.40
     however
    0.39
    Act Density 0.017%

    No Known Activations