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

    Neuronpedia

    INDEX
    Explanations

    references to developers and developer resources

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

    software developer contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    束
    -0.42
     Serikat
    -0.41
     Semoga
    -0.40
    Semoga
    -0.38
    rifft
    -0.38
    Abraços
    -0.38
     resep
    -0.37
     çerçe
    -0.36
     tæ
    -0.36
     środ
    -0.36
    POSITIVE LOGITS
    developer
    2.89
    Developer
    2.44
     Developer
    2.39
     developer
    2.23
     Developers
    1.55
    developers
    1.52
    Developers
    1.47
     developers
    1.37
     Entwick
    1.26
    开发者
    1.16
    Act Density 0.006%

    No Known Activations