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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     конечно
    -0.08
    🐳
    -0.07
    	pop
    -0.07
    まあ
    -0.07
    _learn
    -0.07
     seedu
    -0.07
     обычно
    -0.07
    /******/
    -0.07
     Kee
    -0.07
    낟
    -0.07
    POSITIVE LOGITS
    igh
    0.08
     IX
    0.07
     adverse
    0.07
    itz
    0.06
     Kash
    0.06
     outfits
    0.06
    bj
    0.06
     lặng
    0.06
     ℝ
    0.06
    fast
    0.06
    Act Density 0.199%

    No Known Activations