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

    Neuronpedia

    INDEX
    Explanations

    output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    facet
    -0.28
     Downs
    -0.25
    å®īåİ¿
    -0.25
    è¡İ
    -0.24
     approving
    -0.24
    umpy
    -0.24
    ibs
    -0.23
     facet
    -0.23
    ä¿Ĭ
    -0.23
     Watches
    -0.23
    POSITIVE LOGITS
    ä¹°åĪ°
    0.28
    }{↵
    0.25
     WWW
    0.25
    ewing
    0.25
    她们
    0.25
    ormal
    0.25
     nữa
    0.25
    arine
    0.24
    latex
    0.24
    çļĦåĬ¨åĬĽ
    0.24
    Act Density 0.020%

    No Known Activations