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

    Neuronpedia

    INDEX
    Explanations

    clear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ө
    -0.09
     өм
    -0.08
     სიცოცხ
    -0.08
     მიმ
    -0.08
     countdown
    -0.08
    ctions
    -0.08
     ны
    -0.08
     ცხოვრ
    -0.08
     Momentum
    -0.08
     hauptsächlich
    -0.08
    POSITIVE LOGITS
     obvious
    0.09
     évident
    0.09
     evidente
    0.09
     очевид
    0.09
     blatant
    0.09
     vanzelf
    0.09
     évid
    0.08
     clare
    0.08
    Accessible
    0.08
     claras
    0.08
    Act Density 0.006%

    No Known Activations