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

    Neuronpedia

    INDEX
    Explanations

    concepts and abstract ideas

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

    "idea" or its variations

    np_acts-logits-general · gemini-2.0-flash

    idea or Idebenone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </em>
    -0.69
    ç
    -0.58
    yam
    -0.54
     Marte
    -0.54
    quiv
    -0.52
    cc
    -0.52
     Wal
    -0.52
    in
    -0.52
    p
    -0.51
     SH
    -0.50
    POSITIVE LOGITS
     ideas
    1.67
     IDEA
    1.67
    Idea
    1.59
     Ideas
    1.59
    ideas
    1.57
    Ideas
    1.57
     Idea
    1.52
    IDEA
    1.47
     IDEAS
    1.41
    idea
    1.37
    Act Density 0.047%

    No Known Activations