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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations and comparisons involving numbers and operations

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

    numbers with decimals and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.44
    DrawerToggle
    -0.39
     integridad
    -0.39
    :✨
    -0.39
     cuero
    -0.37
     ocasión
    -0.37
    Personendaten
    -0.37
     Trä
    -0.36
     CreateTagHelper
    -0.36
     tajam
    -0.36
    POSITIVE LOGITS
    ########.
    0.53
    ----</
    0.47
     Coo
    0.46
     Loops
    0.46
    OGND
    0.46
     виправивши
    0.46
     loops
    0.44
     informée
    0.44
     Hara
    0.43
    ⏟
    0.43
    Act Density 0.939%

    No Known Activations