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

    Neuronpedia

    INDEX
    Explanations

    national interest

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ................................
    -0.07
     Destination
    -0.07
     reviewed
    -0.07
    	form
    -0.07
     paradigm
    -0.07
    -response
    -0.07
     source
    -0.06
     historian
    -0.06
     Evelyn
    -0.06
     cooperative
    -0.06
    POSITIVE LOGITS
    .ham
    0.06
    -sl
    0.06
    ALLE
    0.06
    <<<<
    0.06
     Rit
    0.06
    âl
    0.06
    fail
    0.06
    αλ
    0.06
    าด
    0.06
    FillColor
    0.06
    Act Density 0.050%

    No Known Activations