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

    Neuronpedia

    INDEX
    Explanations

    Organization:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parlare
    0.42
     treo
    0.42
    IBAction
    0.40
     bedste
    0.40
     Gorb
    0.39
     pembang
    0.39
     LPARAM
    0.39
     conversar
    0.39
     richt
    0.39
     particolarmente
    0.38
    POSITIVE LOGITS
    잃
    0.53
    блон
    0.46
     गलत
    0.45
     చక్కెర
    0.44
     Тер
    0.43
    ăr
    0.42
     Об
    0.42
    plastics
    0.42
    ěl
    0.42
    जेक्ट
    0.41
    Act Density 0.007%

    No Known Activations