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

    Neuronpedia

    INDEX
    Explanations

    document metadata and structure markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मोठा
    0.40
    té
    0.40
     bulundu
    0.38
    ől
    0.38
    né
    0.38
     پاورپوینت
    0.38
    links
    0.38
     बनाते
    0.38
     Wie
    0.37
     හර
    0.37
    POSITIVE LOGITS
    Copyright
    0.42
    Presented
    0.41
     work
    0.40
     Present
    0.40
     Presented
    0.40
    Prepared
    0.40
     Copyright
    0.39
    াইট
    0.39
     present
    0.39
     Installed
    0.39
    Act Density 0.002%

    No Known Activations