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

    Neuronpedia

    INDEX
    Explanations

    references to columns and their attributes within data or table structures

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

    column or names starting with Col

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fraid
    -0.56
    دانشنامهٔ
    -0.53
     XCTest
    -0.51
     Taktlose
    -0.51
     Autorizaciones
    -0.51
     présidenti
    -0.51
    RTLD
    -0.51
     Verdad
    -0.50
    advantage
    -0.50
     noDo
    -0.50
    POSITIVE LOGITS
     Col
    1.01
    Col
    0.94
     col
    0.91
    col
    0.91
     COL
    0.87
     Colman
    0.74
     TableColumn
    0.73
    COL
    0.73
    Cols
    0.72
     cols
    0.72
    Act Density 0.016%

    No Known Activations