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

    Neuronpedia

    INDEX
    Explanations

    medical conditions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fy
    -0.07
     Applied
    -0.07
     GF
    -0.06
    generator
    -0.06
    cert
    -0.06
     prelim
    -0.06
    Fixed
    -0.06
     Institutional
    -0.06
    dw
    -0.06
    	bl
    -0.06
    POSITIVE LOGITS
     просто
    0.07
    .neg
    0.07
     bracket
    0.06
                     ↵
    0.06
     göz
    0.06
    ้ค
    0.06
     sürede
    0.06
     intersect
    0.06
     czy
    0.06
    ♀♀
    0.06
    Act Density 0.048%

    No Known Activations