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

    Neuronpedia

    INDEX
    Explanations

    the abstract noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متعلقه
    0.20
     situatie
    0.19
     sytu
    0.19
     kamer
    0.19
     kome
    0.19
     jego
    0.18
     sobbing
    0.18
     insgesamt
    0.18
     její
    0.17
     seiner
    0.17
    POSITIVE LOGITS
     ability
    0.35
     concept
    0.33
     importance
    0.33
     use
    0.33
     role
    0.29
    importance
    0.29
     creation
    0.29
     prevalence
    0.29
     idea
    0.28
     Importance
    0.28
    Act Density 0.149%

    No Known Activations