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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    finaly
    0.71
    បញ្ចប់
    0.69
     उत्तर
    0.63
    ulture
    0.63
     Thoreau
    0.63
     Nain
    0.61
     यादव
    0.59
    felter
    0.59
    📼
    0.59
    flug
    0.58
    POSITIVE LOGITS
    ↵
    0.86
    چ
    0.64
     desta
    0.63
    ј
    0.63
    чи
    0.62
    ка
    0.59
    ﻣ
    0.59
    の
    0.57
    ھر
    0.56
     compartil
    0.56
    Act Density 0.372%

    No Known Activations