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

    Neuronpedia

    INDEX
    Explanations

    the world, globe, country, nation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kafka
    0.79
     this
    0.68
    ε
    0.66
    Reality
    0.65
     Reality
    0.65
     Does
    0.65
     the
    0.64
    Does
    0.64
     Turned
    0.64
    ంక
    0.63
    POSITIVE LOGITS
     spectrum
    1.54
     globe
    1.50
     country
    1.39
     nation
    1.23
    spectrum
    1.22
    country
    1.12
     entire
    1.12
     archipelago
    1.11
     país
    1.11
     gamut
    1.11
    Act Density 0.066%

    No Known Activations