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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical expressions involving calculations

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

    mathematical problems and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enderror
    -0.43
     contextLoads
    -0.42
     BoxFit
    -0.40
    NUMX
    -0.40
     withal
    -0.39
    leyebilirsiniz
    -0.39
    TemporalType
    -0.37
     encore
    -0.36
    +#+#
    -0.36
    Manbalar
    -0.35
    POSITIVE LOGITS
     autorytatywna
    0.50
     titolata
    0.46
    WillAppear
    0.45
    Autoritní
    0.44
     оригіналу
    0.44
    Cooling
    0.43
     Italijanski
    0.43
    UIKit
    0.42
    fortunes
    0.42
     EconPapers
    0.42
    Act Density 0.092%

    No Known Activations