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

    Neuronpedia

    INDEX
    Explanations

    references to criteria and restrictions in documents

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

    diagnostic criteria

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Emp
    -0.40
     Majefty
    -0.36
     Siv
    -0.36
     Emp
    -0.36
     MF
    -0.35
    Tikang
    -0.35
     expor
    -0.34
    EmployeeId
    -0.34
    tslib
    -0.34
    foly
    -0.33
    POSITIVE LOGITS
    criteria
    2.56
     criteria
    1.87
     Criteria
    1.82
    Criteria
    1.77
     CRITERIA
    1.71
     criterion
    1.49
    criterion
    1.48
     Kriterien
    1.38
    criter
    1.37
     critères
    1.30
    Act Density 0.003%

    No Known Activations