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

    Neuronpedia

    INDEX
    Explanations

    repeated occurrences of the word "can."

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

    ability or potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.61
     تانيه
    -0.56
    rungsseite
    -0.56
    forName
    -0.53
    rinfo
    -0.50
     ffilmiau
    -0.49
    Personensuche
    -0.48
    Portale
    -0.48
    isContained
    -0.47
    ulemon
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.55
     Peut
    0.51
     can
    0.49
     Puede
    0.49
    Puede
    0.47
     capable
    0.46
     può
    0.44
     pouvait
    0.43
     יכול
    0.43
     Pueden
    0.43
    Act Density 0.046%

    No Known Activations