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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inclusion or association of items or groups

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

    including or listing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    مصادر
    -0.51
     AssemblyCompany
    -0.47
    出版年
    -0.46
     contextLoads
    -0.43
    camente
    -0.42
    hlands
    -0.41
    ReusableCell
    -0.41
    yntaxException
    -0.41
    arangay
    -0.40
    verwijspagina
    -0.39
    POSITIVE LOGITS
    including
    0.94
    INCLUDING
    0.85
     including
    0.85
    Including
    0.85
     Including
    0.83
     INCLUDING
    0.79
     incluindo
    0.75
     waaronder
    0.74
     includes
    0.74
     incluyendo
    0.72
    Act Density 0.144%

    No Known Activations