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

    Neuronpedia

    INDEX
    Explanations

    features, risks, deceleration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uncountable
    0.42
     Lal
    0.41
     sats
    0.39
    鳎
    0.39
     ওঠে
    0.39
     Persistent
    0.39
     উঠি
    0.38
     Lala
    0.38
    ränkt
    0.38
    යේ
    0.38
    POSITIVE LOGITS
    还
    0.43
     அதே
    0.42
     pedestrians
    0.42
     ugyan
    0.41
     অনুরূপ
    0.41
     আরো
    0.41
     భ
    0.40
    دارة
    0.40
    لم
    0.40
    According
    0.40
    Act Density 0.012%

    No Known Activations