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

    Neuronpedia

    INDEX
    Explanations

    sentence segmentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     வாய
    0.59
    ByAppending
    0.53
    ﺔ
    0.51
     бушлай
    0.51
     مین
    0.50
     EET
    0.50
     പുതിയ
    0.50
     Rück
    0.50
     電気
    0.50
    代わりに
    0.49
    POSITIVE LOGITS
    rs
    0.54
    h
    0.50
    anderen
    0.48
     vies
    0.46
    a
    0.45
    gon
    0.43
    iding
    0.42
    ienten
    0.42
    encion
    0.42
     teams
    0.41
    Act Density 0.001%

    No Known Activations