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

    Neuronpedia

    INDEX
    Explanations

    elements related to image processing attributes

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

    "Tag" followed by a name and number

    np_acts-logits-general · gemini-2.0-flash

    defining tags or headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DeleteBehavior
    -0.64
    )"),
    -0.56
     }}$}
    -0.53
     <=",
    -0.53
    )");
    -0.52
     useNavigate
    -0.52
     akka
    -0.51
     poul
    -0.51
    __":
    -0.49
     resourceCulture
    -0.48
    POSITIVE LOGITS
     header
    1.08
    Header
    0.99
     Header
    0.97
    header
    0.97
     metadata
    0.94
     HEADER
    0.81
    HEADER
    0.79
     headers
    0.77
    metadata
    0.76
    getHeader
    0.74
    Act Density 0.594%

    No Known Activations