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

    Neuronpedia

    INDEX
    Explanations

    explaining open-weights model source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     файлы
    0.77
     reprints
    0.69
     licensing
    0.69
     licensees
    0.66
    컨
    0.64
    Licenses
    0.63
     Licensing
    0.63
     demurrer
    0.61
    createServer
    0.61
     Licenses
    0.60
    POSITIVE LOGITS
     source
    0.98
    source
    0.84
     مصدر
    0.83
    Source
    0.82
     Source
    0.77
     sumber
    0.77
     источник
    0.76
    Sk
    0.74
     sources
    0.72
     किताब
    0.72
    Act Density 0.071%

    No Known Activations