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

    Neuronpedia

    INDEX
    Explanations

    academic year or exam context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cllr
    0.47
     dwarves
    0.44
    Cllr
    0.44
     GCSE
    0.43
     dwarf
    0.42
     toddlers
    0.41
    neighbour
    0.40
     Midlands
    0.39
     cider
    0.39
     dwar
    0.39
    POSITIVE LOGITS
     HSC
    0.64
     Sac
    0.56
     SAC
    0.55
     Year
    0.52
     AT
    0.50
     TSS
    0.50
     sac
    0.49
     स्टडी
    0.48
     HSP
    0.48
     Prel
    0.48
    Act Density 0.003%

    No Known Activations