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

    Neuronpedia

    INDEX
    Explanations

    names and titles of organizations and businesses

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

    multi-token phrases and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chiaramente
    -0.36
     Widerspruch
    -0.35
    fassen
    -0.35
     recuer
    -0.34
     hayan
    -0.34
     comunque
    -0.33
     değildir
    -0.33
     purtroppo
    -0.32
     given
    -0.31
     either
    -0.31
    POSITIVE LOGITS
    OGND
    0.75
     ujednoznacz
    0.64
    ########.
    0.64
    ImageContext
    0.62
    Diweddarwch
    0.61
    WriteTagHelper
    0.57
     invokingState
    0.57
     BorderRadius
    0.57
     companyId
    0.56
     MenuView
    0.56
    Act Density 0.019%

    No Known Activations