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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ScreenState
    -0.06
     Cabin
    -0.06
    UserProfile
    -0.06
     aslında
    -0.06
     jaký
    -0.06
     analog
    -0.06
    .config
    -0.06
     }),↵
    -0.06
    からない
    -0.06
     फल
    -0.06
    POSITIVE LOGITS
    :N
    0.07
    ению
    0.07
    ulations
    0.07
    ysi
    0.06
     setIs
    0.06
     Sunni
    0.06
    сия
    0.06
     django
    0.06
    /QĐ
    0.06
     checker
    0.06
    Act Density 0.003%

    No Known Activations