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

    Neuronpedia

    INDEX
    Explanations

    Names starting with Vij

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Face
    -0.07
    alsa
    -0.07
    мента
    -0.07
     sel
    -0.07
     pools
    -0.06
    elon
    -0.06
    Sel
    -0.06
     состояния
    -0.06
    Hello
    -0.06
     이벤트
    -0.06
    POSITIVE LOGITS
     männ
    0.07
     měsí
    0.06
    closing
    0.06
     чин
    0.06
    ｭ
    0.06
     MBA
    0.06
     keyValue
    0.06
     threading
    0.06
     Manson
    0.06
     сайті
    0.06
    Act Density 0.011%

    No Known Activations