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

    Neuronpedia

    INDEX
    Explanations

    references to fitness and wellness programs

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

    you don't have to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.59
    Хьажоргаш
    -0.54
    InjectAttribute
    -0.50
     autorytatywna
    -0.45
    OGND
    -0.45
    ftagPool
    -0.43
     resourceCulture
    -0.42
    Produzione
    -0.40
    deelte
    -0.40
    tonode
    -0.39
    POSITIVE LOGITS
     reaſon
    0.45
     Inſ
    0.43
     laſt
    0.42
     Chriftian
    0.42
     BoxFit
    0.40
    elow
    0.39
     queſta
    0.39
     eſt
    0.38
     guarn
    0.38
     Anſ
    0.38
    Act Density 0.019%

    No Known Activations