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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    spacer
    -0.07
     sonrası
    -0.07
     trval
    -0.07
     Θ
    -0.07
     саме
    -0.06
     Bilder
    -0.06
     blacklist
    -0.06
    Robert
    -0.06
     Tillerson
    -0.06
    Dependencies
    -0.06
    POSITIVE LOGITS
     briefing
    0.06
    film
    0.06
    "){
    0.06
     mHandler
    0.06
    ispers
    0.06
    .Restrict
    0.06
     〈
    0.06
    (){↵
    0.06
     청
    0.06
     listen
    0.06
    Act Density 0.015%

    No Known Activations