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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names

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

    names following first names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.50
    يميديا
    -0.47
     kaarangay
    -0.45
     beginnetje
    -0.45
     XCTest
    -0.44
    getMinutes
    -0.43
     utafitiHapana
    -0.43
     [*]
    -0.42
    ngr
    -0.42
     JpaRepository
    -0.42
    POSITIVE LOGITS
     noDo
    0.55
     wikipagina
    0.47
     oreille
    0.45
     Klassen
    0.41
     tatuagem
    0.40
    Puis
    0.40
    Dean
    0.40
     بيها
    0.38
    Donovan
    0.37
     Donovan
    0.37
    Act Density 0.074%

    No Known Activations