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

    Neuronpedia

    INDEX
    Explanations

    inventory and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    empat
    0.75
     letters
    0.74
    electrons
    0.73
    efficients
    0.73
    莅
    0.73
    divided
    0.67
    oso
    0.67
    メリット
    0.67
     pís
    0.66
     لباس
    0.66
    POSITIVE LOGITS
     repertoire
    1.60
     arsenal
    1.39
     inventory
    1.36
     lexicon
    1.31
     inventories
    1.29
     списке
    1.25
     list
    1.24
     roster
    1.23
     shelves
    1.19
     queue
    1.17
    Act Density 0.260%

    No Known Activations