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

    Neuronpedia

    INDEX
    Explanations

    temple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     researched
    -0.07
     عالية
    -0.07
    죠
    -0.06
    icích
    -0.06
    .an
    -0.06
     olmadı
    -0.06
    _EXISTS
    -0.06
     iii
    -0.06
    .Car
    -0.06
    MEDIA
    -0.06
    POSITIVE LOGITS
    roscope
    0.06
    grow
    0.06
     Dean
    0.06
    175
    0.06
     ancient
    0.06
    aussian
    0.06
     tm
    0.06
     preserve
    0.06
     ubiqu
    0.06
     evaluator
    0.06
    Act Density 0.007%

    No Known Activations