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

    Neuronpedia

    INDEX
    Explanations

    references to established standards and guidelines in various contexts

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

    standards and guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ьаж
    -0.47
     onPostExecute
    -0.40
    delwed
    -0.39
    undi
    -0.37
    PostExecute
    -0.37
    ++
    -0.37
    principalColumn
    -0.36
     sarcastic
    -0.36
     Parrish
    -0.36
    castic
    -0.36
    POSITIVE LOGITS
     standards
    1.06
    standards
    1.02
    Standards
    0.96
     Standards
    0.94
     STANDARDS
    0.83
     guidelines
    0.78
     standardization
    0.75
     standard
    0.73
     normes
    0.73
     estándares
    0.72
    Act Density 0.100%

    No Known Activations