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

    Neuronpedia

    INDEX
    Explanations

    Code/text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     opener
    -0.28
    onte
    -0.27
    serrat
    -0.25
     EditorGUI
    -0.25
     opening
    -0.25
     ups
    -0.24
    -meta
    -0.24
     Diploma
    -0.23
     Opening
    -0.23
    ÑħоÑĤ
    -0.23
    POSITIVE LOGITS
     Objects
    0.28
    imat
    0.26
    imore
    0.26
    Objects
    0.25
    Posting
    0.24
     Rosenberg
    0.24
     Posting
    0.24
    äºĺ
    0.24
    èĥ¤
    0.24
    èĮ¹
    0.24
    Act Density 1.344%

    No Known Activations