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

    Neuronpedia

    INDEX
    Explanations

    the presence of the term "Ned" or related variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentionned, lied, or Ned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GroupLayout
    -0.57
    modelBuilder
    -0.56
     Firestone
    -0.54
    principalTable
    -0.53
    photobucket
    -0.53
     CreateTagHelper
    -0.53
    NameInMap
    -0.52
    ArgumentParser
    -0.51
    aspectj
    -0.51
     otomatig
    -0.51
    POSITIVE LOGITS
     Ned
    2.47
    Ned
    2.41
     ned
    1.73
     NED
    1.69
    NED
    1.59
    ned
    1.38
     Neder
    0.95
    Neder
    0.88
     Nes
    0.75
     Nied
    0.75
    Act Density 0.002%

    No Known Activations