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

    Neuronpedia

    INDEX
    Explanations

    technological advancements and breakthroughs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eggi
    0.40
     toekom
    0.39
    潜在
    0.38
    剝
    0.38
    首相
    0.37
    dig
    0.37
     nantinya
    0.37
     ಅಂಶ
    0.36
    extensive
    0.36
     থাকে
    0.36
    POSITIVE LOGITS
     advancements
    0.78
     advances
    0.75
    推动
    0.74
     developments
    0.71
     spearheaded
    0.69
     innovations
    0.64
     breakthroughs
    0.64
     advancement
    0.63
     pushing
    0.61
     avances
    0.61
    Act Density 0.041%

    No Known Activations