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

    Neuronpedia

    INDEX
    Explanations

    references to trustworthiness or reliability in data or sources

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

    trusted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gass
    -0.49
    璋
    -0.49
    SBATCH
    -0.48
     all
    -0.47
    setVerticalGroup
    -0.47
     sort
    -0.46
    aabb
    -0.46
    changelog
    -0.45
    tickets
    -0.45
     deport
    -0.45
    POSITIVE LOGITS
     trusted
    2.11
     Trusted
    2.08
    trusted
    1.95
    Trusted
    1.84
     trustworthy
    1.13
     vertrou
    1.04
    rusted
    0.96
     trusty
    0.95
     reliable
    0.93
     विश्वसनीय
    0.93
    Act Density 0.003%

    No Known Activations