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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dedication
    -0.08
    🅓
    -0.07
     largely
    -0.06
    nel
    -0.06
    僅
    -0.06
     newList
    -0.06
    éo
    -0.06
     hailed
    -0.06
     adap
    -0.06
    ăn
    -0.06
    POSITIVE LOGITS
    (outputs
    0.08
     Dummy
    0.07
     Pants
    0.07
    prites
    0.07
    truck
    0.07
    (service
    0.07
     Syntax
    0.07
    EntityManager
    0.07
     SUCCESS
    0.07
     Layer
    0.07
    Act Density 0.034%

    No Known Activations