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
     unit
    -0.07
     MAS
    -0.07
     aspect
    -0.06
     pods
    -0.06
    ())))↵
    -0.06
     dimension
    -0.06
     หร
    -0.06
    .getType
    -0.06
    \Abstract
    -0.06
    논
    -0.06
    POSITIVE LOGITS
    提出
    0.07
    ерап
    0.06
     aracı
    0.06
    ρωση
    0.06
     дорог
    0.06
    ●
    0.06
    луата
    0.06
    ",$
    0.06
     incumb
    0.06
    ियम
    0.06
    Act Density 0.006%

    No Known Activations