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

    Neuronpedia

    INDEX
    Explanations

    specific references to safety standards and regulations

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

    such as or particular

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.60
    BibitemShut
    -0.56
     arşivlendi
    -0.54
     utafitiHapana
    -0.54
    archiviato
    -0.52
    Bibitem
    -0.52
    uei
    -0.50
     оригіналу
    -0.50
    biamo
    -0.49
     ujednoznacz
    -0.49
    POSITIVE LOGITS
     Special
    0.38
    ="../../
    0.37
     Specialist
    0.37
     specialist
    0.35
    '][$
    0.35
     sile
    0.34
    specialist
    0.32
     SPECIAL
    0.32
     especial
    0.32
     va
    0.32
    Act Density 0.055%

    No Known Activations