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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and variables related to functions or equations

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

    derivatives with respect to x

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createState
    -0.37
     pure
    -0.35
     rallado
    -0.33
    vertra
    -0.31
    delwed
    -0.31
     Había
    -0.31
     Comprometido
    -0.31
    ReusableCell
    -0.31
     mag
    -0.31
    agisse
    -0.31
    POSITIVE LOGITS
     esternos
    0.58
    BibitemShut
    0.56
     يتيمه
    0.54
    niſſe
    0.54
     informée
    0.53
    citenamefont
    0.52
     deleteUser
    0.50
    levance
    0.50
     deleteById
    0.50
    WebMethod
    0.49
    Act Density 0.357%

    No Known Activations