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

    Neuronpedia

    INDEX
    Explanations

    environment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     welding
    -0.08
     clon
    -0.08
     AC
    -0.08
     IDs
    -0.08
    IDs
    -0.08
     circuito
    -0.07
    orda
    -0.07
     Experiment
    -0.07
     více
    -0.07
     پروگرام
    -0.07
    POSITIVE LOGITS
    External
    0.10
     looming
    0.10
    external
    0.10
     الخارجية
    0.10
     externos
    0.10
     geopolitical
    0.09
     foreseeable
    0.09
     External
    0.09
    environment
    0.09
     hostile
    0.09
    Act Density 0.004%

    No Known Activations