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

    Neuronpedia

    INDEX
    Explanations

    dialogue questioning the truth or intentions of others

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

    Appearing before or after a question

    np_acts-logits-general · gemini-2.0-flash

    conversational transitions and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ślę
    -0.70
     AppCompatTheme
    -0.68
    "):
    -0.65
    AnimationsModule
    -0.64
    '):
    -0.63
     myſelf
    -0.62
     itſelf
    -0.62
     cetera
    -0.62
    ();)
    -0.62
     Efq
    -0.62
    POSITIVE LOGITS
    ագրություններ
    0.58
    PageRoute
    0.48
    avax
    0.48
    onomía
    0.48
    告
    0.45
    ãng
    0.45
    coe
    0.45
    告诉我
    0.44
    literal
    0.42
     meaning
    0.42
    Act Density 0.128%

    No Known Activations