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

    Neuronpedia

    INDEX
    Explanations

    references to descriptions in text or data structures

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

    description keyword or field

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "..\..\..\
    -0.52
     "..\..\
    -0.51
    toHaveBeenCalled
    -0.50
     yyq
    -0.47
    illotine
    -0.45
    columnNumber
    -0.43
    ⎩
    -0.43
     <<<<<<<<<<<<<<
    -0.43
    せっかく
    -0.43
    anément
    -0.43
    POSITIVE LOGITS
    setDescription
    0.91
     description
    0.90
    description
    0.78
    getDescription
    0.76
     setDescription
    0.72
     descrizione
    0.70
     descriptions
    0.68
     descripcion
    0.68
     descrip
    0.68
     Description
    0.68
    Act Density 0.007%

    No Known Activations