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

    Neuronpedia

    INDEX
    Explanations

    words and parts of words associated with certain suffixes or morphemes

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

    non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Litteratur
    -0.39
    ưng
    -0.32
     öffnungszeiten
    -0.32
     commerciaux
    -0.32
     abstrait
    -0.31
     itſelf
    -0.31
     Tätigkeit
    -0.31
     préférences
    -0.30
     París
    -0.30
     müh
    -0.30
    POSITIVE LOGITS
    Datuak
    0.69
    Autoritní
    0.66
    ########.
    0.63
    béco
    0.60
    0.59
    Rhestr
    0.58
     متحده
    0.58
     <<<<<<<<<<<<<<
    0.58
    astify
    0.57
     okuyayım
    0.57
    Act Density 0.207%

    No Known Activations