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

    Neuronpedia

    INDEX
    Explanations

    comprehension

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mj
    -0.07
    Sy
    -0.07
     fatalities
    -0.07
     Registrar
    -0.07
     Alberta
    -0.07
     ance
    -0.06
     �
    -0.06
    Gap
    -0.06
    Dia
    -0.06
    vect
    -0.06
    POSITIVE LOGITS
     comprehension
    0.07
     использу
    0.07
    -short
    0.06
     compreh
    0.06
     Tmax
    0.06
     Philadelphia
    0.06
     ayrıca
    0.06
     скор
    0.06
     comprehend
    0.06
     appropriated
    0.06
    Act Density 0.006%

    No Known Activations