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

    Neuronpedia

    INDEX
    Explanations

    cities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    350
    -0.06
    Looper
    -0.06
    ogn
    -0.06
    arrays
    -0.06
    .Start
    -0.06
     Aux
    -0.06
    Pool
    -0.06
     rapid
    -0.06
    گز
    -0.05
     Fatal
    -0.05
    POSITIVE LOGITS
     उस
    0.07
    社区
    0.07
     выбра
    0.07
     white
    0.06
    	nil
    0.06
     кал
    0.06
    "type
    0.06
     usa
    0.06
    :/
    0.06
    ();)
    0.06
    Act Density 0.048%

    No Known Activations