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

    Neuronpedia

    INDEX
    Explanations

    website page content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     demand
    -0.08
    IRROR
    -0.06
    ่วย
    -0.06
    structor
    -0.06
    utches
    -0.06
    الم
    -0.06
    атель
    -0.06
     TERM
    -0.06
     AND
    -0.06
    	level
    -0.06
    POSITIVE LOGITS
    -----------↵↵
    0.07
     ';↵
    0.06
     Grammar
    0.06
    "]){↵
    0.06
    Formatting
    0.06
    xxxxxxxx
    0.06
    .Utc
    0.06
     Timing
    0.06
    ();↵↵↵
    0.06
     {↵↵↵
    0.06
    Act Density 0.021%

    No Known Activations