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

    Neuronpedia

    INDEX
    Explanations

    shifting functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gum
    -0.08
    ,
    -0.08
     rapper
    -0.08
     religion
    -0.08
     heer
    -0.07
     בר
    -0.07
     smr
    -0.07
     norm
    -0.07
     assicur
    -0.07
     robh
    -0.07
    POSITIVE LOGITS
     {}
↵
↵
    0.08
     préalable
    0.08
     Centennial
    0.08
     కేంద్ర
    0.08
    {
↵
↵
    0.08
     cierta
    0.08
     官网
    0.08
    usu
    0.07
     центра
    0.07
     이동
    0.07
    Act Density 0.030%

    No Known Activations