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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اصيل
    -0.06
    .FIELD
    -0.06
     RestClient
    -0.06
     Rookie
    -0.06
     جنوبی
    -0.06
    NY
    -0.06
     jokes
    -0.06
    eel
    -0.06
    Patient
    -0.06
     Особ
    -0.06
    POSITIVE LOGITS
    Append
    0.07
     Ná
    0.07
     addons
    0.07
     <-
    0.07
     科
    0.07
     συνέ
    0.07
     accepts
    0.06
     Derm
    0.06
    append
    0.06
    -prev
    0.06
    Act Density 0.027%

    No Known Activations