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

    Neuronpedia

    INDEX
    Explanations

    eradication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hanson
    -0.07
     Downloads
    -0.07
     Uses
    -0.07
     withd
    -0.07
    محطة
    -0.07
    .GetResponse
    -0.07
    .Serial
    -0.07
     totally
    -0.07
     Magn
    -0.07
     kullan
    -0.07
    POSITIVE LOGITS
     المستوى
    0.07
    QUEST
    0.07
    ulent
    0.07
    黨
    0.06
    Runnable
    0.06
    hurst
    0.06
    setType
    0.06
    军
    0.06
    这部
    0.06
    ..."↵
    0.06
    Act Density 0.008%

    No Known Activations