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

    Neuronpedia

    INDEX
    Explanations

    producer/consumer pattern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cache
    0.46
     Theorem
    0.45
     Ridge
    0.43
     Picasso
    0.43
     Arts
    0.43
     Assy
    0.43
    ViewModel
    0.42
     Denim
    0.42
     Earth
    0.42
     Terrain
    0.42
    POSITIVE LOGITS
     communist
    0.52
     socialist
    0.50
     operatives
    0.49
    規制
    0.48
    人士
    0.48
    COMPANY
    0.48
    MAIL
    0.47
    NETWORK
    0.46
     ideology
    0.46
    NON
    0.46
    Act Density 0.020%

    No Known Activations