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

    Neuronpedia

    INDEX
    Explanations

    lists numbers and letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inorder
    0.20
     antecedent
    0.19
     computes
    0.19
     interconnect
    0.19
     svm
    0.19
    Upon
    0.18
    "=>
    0.18
    ρίου
    0.18
     alternates
    0.18
     approx
    0.17
    POSITIVE LOGITS
     Maybe
    0.35
     It
    0.34
     Hopefully
    0.32
     Everything
    0.31
     Things
    0.31
     Something
    0.31
     Nothing
    0.30
     😉
    0.30
     Nobody
    0.30
     Especially
    0.29
    Act Density 0.607%

    No Known Activations