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

    Neuronpedia

    INDEX
    Explanations

    configure, configuration, rules, policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chiffon
    0.45
     alkaloids
    0.45
     cercano
    0.43
     phenomenology
    0.42
     retelling
    0.42
    Hilbert
    0.41
     interdiscipl
    0.41
     electrochemical
    0.40
    ConsoleText
    0.40
     fusc
    0.40
    POSITIVE LOGITS
     configured
    1.59
    配置
    1.44
     configuring
    1.38
     configure
    1.37
     configuration
    1.35
     configurations
    1.30
     Configuring
    1.30
     Configure
    1.28
     Configuration
    1.27
    configured
    1.27
    Act Density 0.075%

    No Known Activations