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

    Neuronpedia

    INDEX
    Explanations

    Japanese words or phrases indicating emphasis or confirmation

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

    Japanese confirmation or inquiry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iI
    -0.56
    iin
    -0.54
    isis
    -0.52
    IImage
    -0.52
    iti
    -0.52
    iid
    -0.52
    Viri
    -0.51
    itie
    -0.51
    Miri
    -0.50
    Mire
    -0.49
    POSITIVE LOGITS
    ConverterFactory
    0.54
    newVal
    0.52
    cartão
    0.51
    Cancer
    0.51
     gând
    0.50
    cancer
    0.50
    Archae
    0.48
     tanned
    0.48
    hasMany
    0.47
    hôpital
    0.47
    Act Density 0.219%

    No Known Activations