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

    Neuronpedia

    INDEX
    Explanations

    conversational elements and expressions of uncertainty

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

    relative clauses or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zędu
    -0.37
     geschützt
    -0.35
    ToDouble
    -0.34
    обходимо
    -0.34
     посвящен
    -0.34
     urgencia
    -0.33
     annuelle
    -0.33
     utafitiHapana
    -0.33
    ])/
    -0.32
     которое
    -0.32
    POSITIVE LOGITS
     who
    2.23
    who
    1.85
     Who
    1.82
    Who
    1.80
     quién
    1.68
     quien
    1.51
    谁
    1.42
     hvem
    1.38
     siapa
    1.36
    Quién
    1.33
    Act Density 0.058%

    No Known Activations