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

    Neuronpedia

    INDEX
    Explanations

    contextual phrases around nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    up
    0.55
    size
    0.51
    are
    0.50
    र्डर
    0.48
    is
    0.48
    if
    0.47
    ade
    0.46
    oble
    0.46
    one
    0.46
    of
    0.45
    POSITIVE LOGITS
     Exo
    0.54
     Fintech
    0.52
     Astronaut
    0.51
     waivers
    0.50
     ASEAN
    0.50
     Futuristic
    0.49
     fibroblasts
    0.49
     Countdown
    0.49
     SMI
    0.49
    টিক
    0.49
    Act Density 0.001%

    No Known Activations