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

    Neuronpedia

    INDEX
    Explanations

    representations of numerical values

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

    numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.58
     resourceCulture
    -0.50
    BoxShadow
    -0.49
    queryInterface
    -0.47
    Diweddarwch
    -0.46
    uilla
    -0.46
     straighten
    -0.46
    matte
    -0.46
    HostException
    -0.45
     physio
    -0.45
    POSITIVE LOGITS
     enfans
    0.57
     âgées
    0.50
     istrinya
    0.49
     peuples
    0.49
     blessés
    0.49
     governador
    0.47
     scelte
    0.46
     Pemain
    0.46
     mijne
    0.46
     heridos
    0.46
    Act Density 0.208%

    No Known Activations