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

    Neuronpedia

    INDEX
    Explanations

    wikipedia.org

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    每天
    0.44
     ง่าย
    0.44
     onboarding
    0.38
    ന്‍റെ
    0.38
    اؤ
    0.38
     trajets
    0.37
     ਤੁਹਾ
    0.37
    رآ
    0.37
     vaše
    0.37
    缐
    0.36
    POSITIVE LOGITS
     Wikipedia
    0.71
     Wikimedia
    0.67
    Wikipedia
    0.64
    Wikimedia
    0.59
    wikipedia
    0.57
     Wiki
    0.55
    wiki
    0.55
     wikipedia
    0.54
     Вики
    0.54
     Vikipedi
    0.54
    Act Density 0.098%

    No Known Activations