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

    Neuronpedia

    INDEX
    Explanations

    specific topic phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     takže
    0.47
    だったので
    0.42
     परीक्षण
    0.42
    妻
    0.41
    しました
    0.41
     therapies
    0.41
    خل
    0.40
     więc
    0.40
    ট্র
    0.40
     slavery
    0.39
    POSITIVE LOGITS
     Debe
    0.43
     precise
    0.41
    心态
    0.40
     자신
    0.40
     auteur
    0.40
     honed
    0.40
     собственного
    0.40
     Precise
    0.39
    เฉพาะ
    0.38
     непосред
    0.38
    Act Density 0.002%

    No Known Activations