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

    Neuronpedia

    INDEX
    Explanations

    directly through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وہ
    0.49
     ი
    0.49
     ď
    0.47
     এর
    0.47
     सफाई
    0.47
     noirs
    0.47
     সংবাদ
    0.46
     сеть
    0.46
     노
    0.46
     එය
    0.45
    POSITIVE LOGITS
    Nothing
    0.49
    encountered
    0.48
    Dok
    0.48
    bim
    0.48
    Те
    0.47
    sandwich
    0.47
    Xiaomi
    0.47
    Bir
    0.46
    Ни
    0.46
    Пра
    0.46
    Act Density 0.000%

    No Known Activations