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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itele
    -0.07
    죄
    -0.07
     brunch
    -0.07
     син
    -0.07
    озі
    -0.07
    ColumnType
    -0.06
     colonization
    -0.06
    Serv
    -0.06
     вет
    -0.06
    (exp
    -0.06
    POSITIVE LOGITS
     neutral
    0.06
    .='
    0.06
    ;charset
    0.06
    =-=-
    0.06
    …but
    0.06
    !"
    0.06
     DISCLAIMER
    0.06
    .deploy
    0.06
    ]").
    0.06
     DI
    0.05
    Act Density 0.231%

    No Known Activations