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

    Neuronpedia

    INDEX
    Explanations

    structural or numeric data, particularly related to coding or programming contexts

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

    First word of a sentence

    np_acts-logits-general · gemini-2.0-flash

    special characters and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    — 
    -0.71
     küche
    -0.68
     Amérique
    -0.60
     specialmente
    -0.58
    достатки
    -0.58
    nexpected
    -0.58
     espagne
    -0.57
     særlig
    -0.57
     spesielt
    -0.57
     weihnachts
    -0.57
    POSITIVE LOGITS
    <bos>
    2.17
    '
    1.00
     виправивши
    0.88
    ’
    0.87
     Мексичка
    0.81
    /*++
    0.77
     فريبيس
    0.74
     Савезне
    0.71
     дописавши
    0.70
    ]")]
    0.69
    Act Density 0.790%

    No Known Activations