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

    Neuronpedia

    INDEX
    Explanations

    data structures and programming constructs related to attributes and objects

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

    XML/HTML attributes

    np_acts-logits-general · gemini-2.0-flash

    attributes and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.57
     Sherry
    -0.52
     Sheridan
    -0.50
     createSlice
    -0.50
     Bane
    -0.49
    Sherry
    -0.48
     Reiner
    -0.48
     Scud
    -0.47
     Hobson
    -0.47
     Nils
    -0.47
    POSITIVE LOGITS
     Att
    2.46
     attribute
    2.37
     att
    2.35
     Attribute
    2.26
     attr
    2.26
    Att
    2.22
    Attribute
    2.18
     attributes
    2.13
    attribute
    2.12
    att
    2.12
    Act Density 0.936%

    No Known Activations