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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical concepts and relationships

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

    equality case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.66
    Tembelea
    -0.64
    Personensuche
    -0.63
    AsUp
    -0.56
    ]")]
    -0.55
    gameserver
    -0.52
    featureID
    -0.52
    tagHelperRunner
    -0.51
     doInBackground
    -0.51
     ligiloj
    -0.50
    POSITIVE LOGITS
    probably
    0.43
     probably
    0.42
    Probably
    0.41
     Probably
    0.40
    max
    0.40
    mejor
    0.40
     MAX
    0.40
    MAX
    0.38
    Mejor
    0.38
    펼
    0.37
    Act Density 0.109%

    No Known Activations