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

    Neuronpedia

    INDEX
    Explanations

    Stoicism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    2.91
    tens
    2.88
    ज
    2.87
    小朋友
    2.69
    society
    2.69
    ва
    2.64
    sia
    2.61
    targets
    2.60
    tfidf
    2.53
    tf
    2.49
    POSITIVE LOGITS
    "${
    2.39
    й
    2.38
    ፍተኛ
    2.28
    ení
    2.09
    ples
    2.01
    年的
    1.99
    િલ્
    1.97
     estampado
    1.95
    ה
    1.94
    в
    1.93
    Act Density 0.004%

    No Known Activations