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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اشت
    -0.08
     إليه
    -0.07
    ष
    -0.07
    kr
    -0.07
    โท
    -0.06
     СП
    -0.06
    .search
    -0.06
    	sl
    -0.06
    Kh
    -0.06
     nullptr
    -0.06
    POSITIVE LOGITS
     GMC
    0.07
     Dylan
    0.07
     depends
    0.07
     borderRadius
    0.06
    ฬ
    0.06
     Ebay
    0.06
     wij
    0.06
     subscribing
    0.06
     rnd
    0.06
    orning
    0.06
    Act Density 0.003%

    No Known Activations