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

    Neuronpedia

    INDEX
    Explanations

    mex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mex
    -2.03
     
    -0.73
    MEX
    -0.68
     p
    -0.56
     an
    -0.56
     a
    -0.55
     pos
    -0.54
     "
    -0.54
    a
    -0.54
     con
    -0.52
    POSITIVE LOGITS
     Efq
    0.94
     itſelf
    0.94
     Majefty
    0.85
     myſelf
    0.84
     iſt
    0.81
     ſeveral
    0.81
     ſind
    0.80
     ſche
    0.80
     ſhe
    0.79
     whoſe
    0.78
    Act Density 0.188%

    No Known Activations