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

    Neuronpedia

    INDEX
    Explanations

    Seat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -alone
    -0.07
    ████
    -0.07
    وروب
    -0.06
     CLASS
    -0.06
    .Serializable
    -0.06
    =F
    -0.06
     dude
    -0.06
    Leaks
    -0.06
    asctime
    -0.06
     floats
    -0.06
    POSITIVE LOGITS
     Extension
    0.06
     江
    0.06
     dent
    0.06
    歳
    0.06
    (Customer
    0.06
    	it
    0.06
     radio
    0.06
     制
    0.06
    rgan
    0.05
    (recipe
    0.05
    Act Density 0.029%

    No Known Activations