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

    Neuronpedia

    INDEX
    Explanations

    words following `[` or `*`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಿಂದ
    0.60
    hypothesis
    0.57
    lemen
    0.57
    학생
    0.54
    Ⴌ
    0.54
     izquierda
    0.53
    兢
    0.52
     অভিব্য
    0.50
    ്യൂ
    0.50
    மேலும்
    0.50
    POSITIVE LOGITS
     stores
    0.52
     à
    0.52
     —
    0.52
     सिक्स
    0.52
    [.
    0.52
     services
    0.51
     percent
    0.51
    être
    0.51
     meng
    0.50
     आप
    0.49
    Act Density 0.000%

    No Known Activations