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

    Neuronpedia

    INDEX
    Explanations

    multilingual text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     répondre
    0.73
    檳
    0.73
     Josephine
    0.72
     Seeds
    0.72
     Qe
    0.72
     muchos
    0.71
     seeds
    0.71
     corresponds
    0.71
     resp
    0.70
     гэ
    0.70
    POSITIVE LOGITS
     বিষয়
    0.82
    ডেম
    0.79
    பாத
    0.78
    續
    0.77
     నగ
    0.77
    日本語
    0.76
     নিয়ন্ত্রণ
    0.75
    <unused48>
    0.75
    وان
    0.75
    ))+
    0.75
    Act Density 0.003%

    No Known Activations