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

    Neuronpedia

    INDEX
    Explanations

    car types

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Biographical
    0.57
     Device
    0.56
     Rhiz
    0.55
     jira
    0.55
     UnityEngine
    0.54
     foaf
    0.54
    Device
    0.54
     MNIST
    0.54
     함수
    0.53
    Fhir
    0.53
    POSITIVE LOGITS
     hatchback
    1.50
     sedan
    1.48
     SUV
    1.43
     SUVs
    1.36
     sporty
    1.35
    车型
    1.31
     powertrain
    1.23
     coupes
    1.20
    SUV
    1.19
     cars
    1.18
    Act Density 0.255%

    No Known Activations