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

    Neuronpedia

    INDEX
    Explanations

    small, abbreviated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     رمض
    -0.08
     Syntax
    -0.07
     Astros
    -0.07
     Reds
    -0.07
    勘探
    -0.07
     dwind
    -0.07
     Laos
    -0.07
    玃
    -0.07
     itemView
    -0.07
    .Gson
    -0.07
    POSITIVE LOGITS
    statement
    0.07
     Thursday
    0.07
    集中
    0.07
    standard
    0.06
     statements
    0.06
    functions
    0.06
    합
    0.06
    Attribute
    0.06
    ########################
    0.06
     overhead
    0.06
    Act Density 0.100%

    No Known Activations