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

    Neuronpedia

    INDEX
    Explanations

    American community history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    реж
    -0.07
    лены
    -0.07
     track
    -0.07
    atology
    -0.06
    cies
    -0.06
     reservation
    -0.06
    ={[
    -0.06
     Puzzle
    -0.06
     dol
    -0.06
     Ø
    -0.06
    POSITIVE LOGITS
     kulak
    0.08
     برنامه
    0.07
    _PROC
    0.07
    기의
    0.06
    _WP
    0.06
                   
↵
    0.06
    Immediately
    0.06
    家
    0.06
     DateFormat
    0.06
    ')
↵
↵
    0.06
    Act Density 0.034%

    No Known Activations