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

    Neuronpedia

    INDEX
    Explanations

    terms related to inclusion or coverage in various contexts

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

    includes or contains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     courtesy
    -0.41
    ❊
    -0.39
    <bos>
    -0.39
    bor
    -0.39
    ather
    -0.39
    stanz
    -0.39
    createQuery
    -0.38
     Wea
    -0.38
     Cran
    -0.38
    stag
    -0.38
    POSITIVE LOGITS
    INCLUDING
    0.93
     mijne
    0.60
     INCLUDING
    0.59
    Including
    0.58
    Contains
    0.57
     zijne
    0.52
     inkluder
    0.52
    Includes
    0.52
    include
    0.51
    ]")]
    0.50
    Act Density 0.002%

    No Known Activations