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

    Neuronpedia

    INDEX
    Explanations

    references to personal identity and cultural background

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

    birthplace or origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Camel
    -0.50
    camel
    -0.50
     Camel
    -0.41
     Nanda
    -0.40
     religieuses
    -0.40
     unloaded
    -0.40
    ItemBackground
    -0.40
     noDo
    -0.40
    bern
    -0.40
    atomic
    -0.40
    POSITIVE LOGITS
    DockStyle
    0.39
     BorderSide
    0.39
    ViewInit
    0.35
    0.34
     familiarity
    0.34
     AssemblyCulture
    0.34
    toThrow
    0.34
    izados
    0.33
    kenstock
    0.33
    titleMargin
    0.32
    Act Density 0.063%

    No Known Activations