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

    Neuronpedia

    INDEX
    Explanations

    highly frequent punctuation marks and conjunctions

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

    initiation of additional information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arangay
    -0.70
    ésultats
    -0.63
    ſcher
    -0.62
     ainfi
    -0.61
    niſſe
    -0.59
    genodigd
    -0.59
     beginnetje
    -0.58
    ulongan
    -0.58
    piec
    -0.57
    cauc
    -0.57
    POSITIVE LOGITS
     Zudem
    0.67
    Inoltre
    0.66
     ayrıca
    0.66
     inoltre
    0.64
     dessutom
    0.64
    Furthermore
    0.63
     Additionally
    0.63
     Furthermore
    0.63
    Additionally
    0.61
     navíc
    0.61
    Act Density 0.054%

    No Known Activations