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

    Neuronpedia

    INDEX
    Explanations

    Volkswagen car models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Iber
    0.46
     Strings
    0.37
    Tracy
    0.37
    膛
    0.37
    Ashley
    0.37
    RECEIVED
    0.37
    烙
    0.37
    пиона
    0.36
     Laur
    0.36
     El
    0.36
    POSITIVE LOGITS
     beetle
    0.84
     Beetle
    0.83
     beetles
    0.79
     camper
    0.71
    beet
    0.64
     Beet
    0.62
     bus
    0.60
     campers
    0.59
     Komb
    0.58
     Camper
    0.58
    Act Density 0.002%

    No Known Activations