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

    Neuronpedia

    INDEX
    Explanations

    elements and their attributes in a structured data format, likely related to programming or software interfaces

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

    Code-related tokens, such as operators or handlers

    np_acts-logits-general · gemini-2.0-flash

    assignments and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlType
    -0.64
    Tikang
    -0.62
    hésite
    -0.61
     OnInit
    -0.60
    DeleteBehavior
    -0.60
    brities
    -0.58
    PRNewswire
    -0.58
    arrêter
    -0.54
     pubblici
    -0.54
    arrête
    -0.53
    POSITIVE LOGITS
     general
    0.58
    bių
    0.51
    Izvori
    0.51
    intValue
    0.50
     non
    0.50
     other
    0.48
    Referències
    0.48
    cella
    0.47
     برانيه
    0.46
     ProtoMessage
    0.45
    Act Density 0.588%

    No Known Activations