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

    Neuronpedia

    INDEX
    Explanations

    Names, especially "Mike"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (IConfiguration
    -0.07
     İnsan
    -0.07
     Pricing
    -0.07
    ovými
    -0.07
     Clarence
    -0.07
     polyester
    -0.06
    postData
    -0.06
    альном
    -0.06
     Say
    -0.06
    LocalizedMessage
    -0.06
    POSITIVE LOGITS
     publisher
    0.07
    _EVENT
    0.06
     japon
    0.06
     mandatory
    0.06
    .event
    0.06
    anel
    0.06
     workouts
    0.06
     surgeon
    0.06
    913
    0.06
     recipients
    0.06
    Act Density 0.010%

    No Known Activations