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

    Neuronpedia

    INDEX
    Explanations

    being

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eager
    -0.07
    憧憬
    -0.07
    温暖
    -0.07
     updated
    -0.07
     my
    -0.07
    产业集群
    -0.06
    析
    -0.06
    mapped
    -0.06
    .placeholder
    -0.06
     DEAL
    -0.06
    POSITIVE LOGITS
     بش
    0.07
    זכיר
    0.07
    CriticalSection
    0.07
    ᶢ
    0.07
    隱私權
    0.07
     subscript
    0.07
     abolition
    0.07
     CL
    0.07
     ta
    0.06
    овой
    0.06
    Act Density 0.080%

    No Known Activations