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

    Neuronpedia

    INDEX
    Explanations

    ORDER WORDS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ни
    0.40
     retired
    0.39
     Trichodesmium
    0.39
     sockfd
    0.38
     vascular
    0.37
     polymer
    0.36
     vector
    0.36
     typedef
    0.36
     bolts
    0.36
    チェーン
    0.36
    POSITIVE LOGITS
    Order
    0.48
     aude
    0.45
     метою
    0.43
    ചെയ്യ
    0.42
     இருந்து
    0.40
    বর্তমান
    0.40
     ordine
    0.40
    QUOTE
    0.40
    ORDER
    0.39
    ordered
    0.39
    Act Density 0.001%

    No Known Activations