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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Imidazole
    0.88
    }}]{
    0.87
    <unused76>
    0.87
    ംഗ്
    0.78
    <unused49>
    0.77
    ዘጋ
    0.76
    <unused42>
    0.73
     katika
    0.73
    Tidak
    0.73
    హ
    0.73
    POSITIVE LOGITS
     and
    2.85
     และ
    2.70
     এবং
    2.54
     आणि
    2.51
     और
    2.50
     và
    2.49
    并且
    2.34
     અને
    2.30
    并
    2.25
     и
    2.22
    Act Density 3.619%

    No Known Activations