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

    Neuronpedia

    INDEX
    Explanations

    specific terms and phrases related to the Turkish language

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

    Non-English language fragments

    np_acts-logits-general · gemini-2.0-flash

    Multilingual and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.89
     houſe
    -0.86
     quæ
    -0.83
     tesettür
    -0.79
     şal
    -0.79
     raiſ
    -0.78
     kılıf
    -0.72
     purpoſe
    -0.72
     yelek
    -0.71
     uſed
    -0.71
    POSITIVE LOGITS
    )
    0.69
    पया
    0.61
    /−
    0.60
    [])
    0.60
    PositiveButton
    0.60
     fieldNum
    0.59
     uska
    0.59
    authorised
    0.58
     bir
    0.58
     postIndex
    0.58
    Act Density 0.010%

    No Known Activations