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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Stretch
    -0.07
     pund
    -0.07
    Trees
    -0.07
     finding
    -0.06
     ′
    -0.06
     smelling
    -0.06
    ром
    -0.06
     gyr
    -0.06
    avelength
    -0.06
     Seymour
    -0.06
    POSITIVE LOGITS
     �
    0.07
    áže
    0.06
     Aval
    0.06
     Curso
    0.06
     recher
    0.06
     См
    0.06
     ngắn
    0.06
     κοι
    0.06
     زیبا
    0.06
     děl
    0.06
    Act Density 0.005%

    No Known Activations