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

    Neuronpedia

    INDEX
    Explanations

    arrival and return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    юр
    0.38
     परमा
    0.38
     <=
    0.36
     Administration
    0.36
     концентра
    0.36
     установлено
    0.36
    వంత
    0.36
     classification
    0.35
     Classification
    0.35
    漉
    0.34
    POSITIVE LOGITS
     back
    0.66
     strolling
    0.59
     knocking
    0.59
     seeking
    0.57
     crawling
    0.57
     visit
    0.56
     bothering
    0.55
     downstairs
    0.53
     sniffing
    0.52
     ashore
    0.51
    Act Density 0.011%

    No Known Activations