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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	glut
    -0.07
    .Model
    -0.06
     loi
    -0.06
    奥
    -0.06
     düzey
    -0.06
    olve
    -0.06
    抓住
    -0.06
    ush
    -0.06
    ,X
    -0.06
    lated
    -0.06
    POSITIVE LOGITS
     bids
    0.08
    uates
    0.07
     orb
    0.07
     README
    0.07
    час
    0.07
    okies
    0.07
     ning
    0.07
    被骗
    0.06
     文件
    0.06
     Ally
    0.06
    Act Density 0.030%

    No Known Activations