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

    Neuronpedia

    INDEX
    Explanations

    java code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pyridine
    0.44
    Subgraph
    0.39
     criss
    0.37
     mornings
    0.37
     axons
    0.35
     varicose
    0.35
     clinched
    0.35
     watercolour
    0.34
     interactivity
    0.34
    纶
    0.33
    POSITIVE LOGITS
    0.55
     System
    0.50
    0.50
    System
    0.50
    0.47
    0.46
    String
    0.45
     String
    0.45
    assertEquals
    0.43
    boolean
    0.41
    Act Density 0.001%

    No Known Activations