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

    Neuronpedia

    INDEX
    Explanations

    copyright, licenses, links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ваются
    0.44
    Copyright
    0.43
     வைத்த
    0.42
    copyright
    0.38
    thumbs
    0.38
     рав
    0.37
     결국
    0.37
    dword
    0.37
     থাকার
    0.36
     rapporti
    0.36
    POSITIVE LOGITS
     repr
    0.39
     licenses
    0.38
    čnih
    0.36
     величе
    0.35
    证券
    0.35
     الأمن
    0.34
     Cus
    0.33
     ચમ
    0.33
     Sche
    0.33
    erre
    0.33
    Act Density 0.010%

    No Known Activations