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

    Neuronpedia

    INDEX
    Explanations

    specific rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ériques
    0.43
    НГ
    0.39
    рити
    0.38
     الفرنسي
    0.38
    корд
    0.37
     criticised
    0.37
    тера
    0.37
     Criticism
    0.37
     क्रिसमस
    0.36
     Соответ
    0.36
    POSITIVE LOGITS
    Ꭻ
    0.42
     visually
    0.41
    納
    0.40
     Nave
    0.38
     रख
    0.37
     Wayne
    0.36
     visible
    0.36
     Egan
    0.36
     naveg
    0.35
     redefining
    0.35
    Act Density 0.000%

    No Known Activations