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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with measurements or parameters

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

    numbers starting with 64

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eſt
    -0.51
     Theſe
    -0.50
    ProductType
    -0.48
    omene
    -0.48
    føl
    -0.48
     ſever
    -0.48
     perſon
    -0.47
     neceſſ
    -0.47
    pkins
    -0.47
     Inſ
    -0.47
    POSITIVE LOGITS
    DidLoad
    0.48
     Danes
    0.48
    それだけ
    0.48
    Personendaten
    0.47
    tagHelperRunner
    0.47
    èdia
    0.46
     Gladstone
    0.45
    flashdata
    0.45
    dank
    0.45
     Hampden
    0.45
    Act Density 0.041%

    No Known Activations