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

    Neuronpedia

    INDEX
    Explanations

    references to identity and self-presentation

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

    image, persona, and facade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    乓
    -0.41
    Обу
    -0.39
    पया
    -0.37
     alfab
    -0.37
     ն
    -0.36
     gantung
    -0.34
    OGND
    -0.34
    Решение
    -0.34
     inš
    -0.34
     doprav
    -0.34
    POSITIVE LOGITS
     persona
    0.64
     facade
    0.52
    XmlAccessType
    0.51
     stereotype
    0.50
     resourceCulture
    0.49
     personality
    0.48
     Persona
    0.48
     image
    0.47
    persona
    0.47
    MethodManager
    0.46
    Act Density 0.229%

    No Known Activations