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

    Neuronpedia

    INDEX
    Explanations

    causality and effects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()["
    -0.07
     livre
    -0.07
    显
    -0.07
     механи
    -0.07
     grou
    -0.06
    .High
    -0.06
    wipe
    -0.06
    roduced
    -0.06
    .Str
    -0.06
    	Set
    -0.06
    POSITIVE LOGITS
    pot
    0.06
    Related
    0.06
     Domino
    0.06
    gren
    0.06
    .mainloop
    0.06
    ﾆﾆﾆﾆ
    0.06
     Teams
    0.06
     engages
    0.06
    inion
    0.06
    	log
    0.06
    Act Density 0.410%

    No Known Activations