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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ct
    -0.07
     testData
    -0.07
     create
    -0.07
    ัส
    -0.07
    -dem
    -0.07
     Ownership
    -0.06
    -no
    -0.06
     rubbed
    -0.06
    -schema
    -0.06
     здоров
    -0.06
    POSITIVE LOGITS
     birisi
    0.07
    되었습니다
    0.07
    eceğini
    0.06
    ubbles
    0.06
    čku
    0.06
     각각
    0.06
     seulement
    0.06
     Elliot
    0.06
     사랑
    0.06
    urgent
    0.05
    Act Density 0.081%

    No Known Activations