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

    Neuronpedia

    INDEX
    Explanations

    longer or larger numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     signatories
    0.42
     transplants
    0.42
    法
    0.41
     mutagenesis
    0.41
     dépos
    0.41
     vendas
    0.40
     putative
    0.40
     licence
    0.39
     pendapatan
    0.39
     polícia
    0.39
    POSITIVE LOGITS
     uncommon
    0.52
    Luckily
    0.49
    複雑
    0.49
     сложные
    0.49
    fortunately
    0.49
    复杂的
    0.48
     distracting
    0.48
     complicating
    0.48
     ง่าย
    0.47
     जटिल
    0.47
    Act Density 0.003%

    No Known Activations