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

    Neuronpedia

    INDEX
    Explanations

    references to legal documents and formal proceedings

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

    followed by legal or informative context

    np_acts-logits-general · gemini-2.0-flash

    describes content of documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writerow
    -0.57
     incapa
    -0.52
     WaitForSeconds
    -0.50
     symbole
    -0.48
     fuma
    -0.48
    EndInit
    -0.48
     tweeting
    -0.47
    Hozzáférés
    -0.46
    KommentareTeilen
    -0.46
     BorderRadius
    -0.45
    POSITIVE LOGITS
     contains
    1.11
     contain
    1.06
    contains
    0.90
     outlines
    0.85
    contain
    0.84
     specifies
    0.84
     states
    0.82
     includes
    0.82
     describes
    0.80
     Contain
    0.77
    Act Density 0.852%

    No Known Activations