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

    Neuronpedia

    INDEX
    Explanations

    JSON Schema

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Postage
    0.45
     pericol
    0.43
     ineligible
    0.42
     hex
    0.40
     Detection
    0.40
    刖
    0.38
     মৌলিক
    0.37
    Elig
    0.37
     נע
    0.37
     இல்லை
    0.36
    POSITIVE LOGITS
    Schema
    1.08
     schema
    1.05
     Schema
    1.03
     schemas
    1.01
    schema
    0.92
    Schemas
    0.90
    SCHEMA
    0.88
     SCHEMA
    0.87
     Sche
    0.83
     validator
    0.77
    Act Density 0.017%

    No Known Activations