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

    Neuronpedia

    INDEX
    Explanations

    Russian/Cyrillic characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     collapse
    -0.08
     fy
    -0.07
     minister
    -0.07
     paragraph
    -0.07
     viability
    -0.07
     firm's
    -0.07
     sara
    -0.07
    Ị
    -0.07
     Candle
    -0.07
    Mp
    -0.07
    POSITIVE LOGITS
    ')↵
    0.09
     |↵
    0.08
    ）、
    0.08
    ;;↵
    0.08
    		↵
    0.08
    0.08
    \\
    0.08
    ；↵
    0.08
    .Inner
    0.08
    　　　　　　　　
    0.08
    Act Density 0.124%

    No Known Activations