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

    Neuronpedia

    INDEX
    Explanations

    references to data extraction and quality assessment processes in research

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

    Manual or automated processes

    np_acts-logits-general · gemini-2.0-flash

    manual coding and review

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MarshalTo
    -0.51
     tartalomajánló
    -0.48
     omge
    -0.47
    fortawesome
    -0.45
    alny
    -0.44
     verwijzen
    -0.44
     BoxDecoration
    -0.43
    asaran
    -0.42
     ivelany
    -0.42
     parç
    -0.42
    POSITIVE LOGITS
     automated
    0.98
     manual
    0.92
     Automated
    0.88
    automated
    0.88
     manually
    0.87
    Automated
    0.86
     automation
    0.85
     manuell
    0.85
    manual
    0.83
     automate
    0.82
    Act Density 0.591%

    No Known Activations