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

    Neuronpedia

    INDEX
    Explanations

    references to standards and standardization

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

    standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noiva
    -0.51
     Joey
    -0.50
     the
    -0.46
    (
    -0.45
     Julie
    -0.43
     Coyle
    -0.43
    Joey
    -0.43
     Meksi
    -0.42
     purses
    -0.42
     putative
    -0.41
    POSITIVE LOGITS
     Standards
    1.20
    Standards
    1.15
     standards
    1.09
    standards
    1.05
     Standard
    1.02
     STANDARDS
    1.02
    Standard
    0.94
     STANDARD
    0.91
    standard
    0.90
     standard
    0.90
    Act Density 0.026%

    No Known Activations