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

    Neuronpedia

    INDEX
    Explanations

    references to environmental variables or configurations

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

    env or environment contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amélioration
    -0.44
     élas
    -0.41
     Stirn
    -0.40
     niega
    -0.39
     muchacha
    -0.39
    Pratique
    -0.37
     administrativo
    -0.37
     élastique
    -0.37
     patata
    -0.37
     Países
    -0.36
    POSITIVE LOGITS
    env
    3.45
    ENV
    2.11
     env
    2.09
    Env
    2.09
     Env
    1.78
     ENV
    1.53
    envs
    1.47
     environment
    1.43
     Environment
    1.36
     Environments
    1.31
    Act Density 0.004%

    No Known Activations