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

    Neuronpedia

    INDEX
    Explanations

    of [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ）
    0.31
     )
    0.31
     أو
    0.31
     رو
    0.30
     รา
    0.30
    ﾗ
    0.30
     details
    0.29
     contents
    0.29
     документы
    0.28
     semblance
    0.28
    POSITIVE LOGITS
     această
    0.48
     tejto
    0.45
     මෙම
    0.41
     této
    0.40
     použití
    0.40
     this
    0.39
     использования
    0.38
     denna
    0.38
     этой
    0.38
     þis
    0.38
    Act Density 0.239%

    No Known Activations