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

    Neuronpedia

    INDEX
    Explanations

    world

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rx
    -0.07
     �
    -0.06
    .Ordinal
    -0.06
     мел
    -0.06
    ]];↵
    -0.06
    icont
    -0.06
    рон
    -0.06
     kicked
    -0.06
     moons
    -0.06
    riangle
    -0.06
    POSITIVE LOGITS
     tel
    0.07
    991
    0.07
    어요
    0.06
    ！↵↵↵↵
    0.06
    @WebServlet
    0.06
     Bert
    0.06
     الأمريكي
    0.06
     canada
    0.06
     disgrace
    0.06
    ený
    0.06
    Act Density 0.000%

    No Known Activations