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

    Neuronpedia

    INDEX
    Explanations

    themes related to self-awareness and personal struggles

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

    sins and imperfections

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects passages about moral failing and the desire for spiritual purification or repentance.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    Ext
    -0.41
    enido
    -0.38
    ext
    -0.38
    Maß
    -0.35
     Италијани
    -0.35
     fortemente
    -0.35
    piecze
    -0.35
     высоким
    -0.35
    ESE
    -0.34
     Colomb
    -0.34
    POSITIVE LOGITS
    Diweddarwch
    0.57
    CppMethod
    0.52
     Infórmanos
    0.50
    SharedCtor
    0.50
    MergeFrom
    0.50
     FetchType
    0.49
     NSCoder
    0.48
    Попис
    0.46
     sins
    0.45
     confessions
    0.45
    Act Density 0.037%

    No Known Activations