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

    Neuronpedia

    INDEX
    Explanations

    legal or academic text related to state and government

    oai_token-act-pair · gemini-2.0-flash

    state

    np_max-act · gemini-2.0-flash

    state

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Negative Logits
     médicaux
    -1.34
     normaux
    -1.27
     sauvages
    -1.27
     automatiques
    -1.25
     nationaux
    -1.24
     industriels
    -1.23
     varandra
    -1.22
     traditionnels
    -1.22
     commerciaux
    -1.21
     feroit
    -1.21
    POSITIVE LOGITS
     set
    0.90
     view
    0.88
     section
    0.86
     number
    0.85
     table
    0.84
     area
    0.82
     figure
    0.82
     work
    0.82
     result
    0.82
     form
    0.82
    Act Density 4.747%

    No Known Activations