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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and discourse markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     તેમજ
    1.31
    Additionally
    1.18
     nonché
    1.13
     sowie
    1.08
     एवं
    1.07
     également
    1.07
     Additionally
    1.07
     oldukça
    1.06
     serta
    1.05
     oraz
    1.04
    POSITIVE LOGITS
    이랑
    1.03
     adesso
    0.98
    တယ်။
    0.95
     stupid
    0.91
    的時候
    0.91
     okay
    0.88
     있으면
    0.85
    니까
    0.84
    이니까
    0.83
     potem
    0.82
    Act Density 0.115%

    No Known Activations