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

    Neuronpedia

    INDEX
    Explanations

    assign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pony
    -0.07
    tainment
    -0.07
     تنظ
    -0.06
     Hogwarts
    -0.06
     mãe
    -0.06
     "@/
    -0.06
    ($"{
    -0.06
    .TAG
    -0.06
     아이디
    -0.06
    옥
    -0.06
    POSITIVE LOGITS
    ісля
    0.07
    Vote
    0.06
    ことは
    0.06
    Bone
    0.06
    诉
    0.06
     cyclists
    0.06
    ्रश
    0.06
    Visitor
    0.06
     ais
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations