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

    Neuronpedia

    INDEX
    Explanations

    references to various types of settings or environments

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

    environments and settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.67
    +#+#
    -0.61
    RefNanny
    -0.60
    contentLoaded
    -0.59
    UrlResolution
    -0.58
    DataContract
    -0.57
    PerformLayout
    -0.55
    StoryboardSegue
    -0.54
    artney
    -0.53
    gdx
    -0.50
    POSITIVE LOGITS
     environment
    0.96
     environments
    0.96
     entornos
    0.78
     Environments
    0.77
     ambientes
    0.72
    环境
    0.69
    environment
    0.68
     ambiente
    0.68
    環境
    0.67
     ambienti
    0.67
    Act Density 0.179%

    No Known Activations