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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating self-reflection or personal experience

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

    personal data or foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.56
    AddTagHelper
    -0.52
     MessageBoxIcon
    -0.52
    sizeCache
    -0.51
    Autoritní
    -0.50
    Бахар
    -0.49
    GraphicsUnit
    -0.48
    InjectAttribute
    -0.46
     препратки
    -0.46
     ferons
    -0.46
    POSITIVE LOGITS
    Personendaten
    0.42
    setVerticalGroup
    0.35
     legend
    0.35
     lion
    0.35
    しま
    0.35
    addGap
    0.34
     gus
    0.34
     Новый
    0.34
     pau
    0.33
     Pente
    0.33
    Act Density 0.013%

    No Known Activations