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

    Neuronpedia

    INDEX
    Explanations

    what/how questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     संसाधनों
    0.39
     అంద
    0.36
    璈
    0.35
     ทั้ง
    0.35
     가능한
    0.35
    瀣
    0.34
     ಭ
    0.34
     наша
    0.34
     aset
    0.33
     хотелось
    0.33
    POSITIVE LOGITS
    3
    0.46
     more
    0.40
     now
    0.39
     Mexico
    0.38
     second
    0.38
     additional
    0.38
     Now
    0.38
     three
    0.37
     further
    0.37
     Wednesday
    0.36
    Act Density 0.038%

    No Known Activations