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

    Neuronpedia

    INDEX
    Explanations

    this/that followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    十分
    0.19
    ynchron
    0.17
    がある
    0.15
    0.15
    Ordinal
    0.15
    ee
    0.14
     across
    0.14
     αλλά
    0.14
    ায়ার
    0.14
    大于
    0.14
    POSITIVE LOGITS
     কাজটি
    0.17
     tejto
    0.17
    ActivityCompat
    0.17
     මෙම
    0.17
     particular
    0.17
     konuda
    0.16
     този
    0.16
     dieses
    0.16
     दौरान
    0.16
     misma
    0.15
    Act Density 0.359%

    No Known Activations