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

    Neuronpedia

    INDEX
    Explanations

    terms related to mental health and its stigma

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

    specific nouns and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.71
    Personendaten
    -0.65
     للاسماء
    -0.62
    الحياه
    -0.59
     للمعارف
    -0.52
    StoreMessageInfo
    -0.50
     miniaturka
    -0.49
     apapun
    -0.49
    青春
    -0.47
     saveiro
    -0.46
    POSITIVE LOGITS
    AxisAlignment
    0.36
     retired
    0.32
    retired
    0.31
     Pension
    0.31
    ねー
    0.30
     بوس
    0.30
    rawDesc
    0.29
    til
    0.29
    pulumi
    0.29
    Wife
    0.28
    Act Density 0.072%

    No Known Activations