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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to artificial intelligence and its applications

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

    artificial intelligence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Provision
    -0.47
    nteral
    -0.44
     Cash
    -0.44
     Provisions
    -0.43
     Recovery
    -0.42
     Pante
    -0.42
    adalajara
    -0.42
     Preliminary
    -0.41
     Showers
    -0.41
     gewel
    -0.41
    POSITIVE LOGITS
     AI
    0.90
    人工智能
    0.74
     inteligencia
    0.63
     Artificial
    0.61
    AI
    0.60
    Artificial
    0.57
     intelligence
    0.57
     intelig
    0.55
     CreateTagHelper
    0.53
     umě
    0.53
    Act Density 0.036%

    No Known Activations