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

    Neuronpedia

    INDEX
    Explanations

    items in a list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused14>
    0.77
     Tamaño
    0.77
     основном
    0.75
    >∕
    0.74
    <unused76>
    0.73
    <unused42>
    0.73
     Приступљено
    0.72
    Imidazole
    0.72
    >\<^
    0.72
    <unused21>
    0.72
    POSITIVE LOGITS
     and
    1.25
     आणि
    1.17
     এবং
    1.17
     और
    1.09
     oraz
    1.09
     และ
    1.08
    以及
    1.06
     và
    1.05
    ,
    1.02
     și
    0.96
    Act Density 0.240%

    No Known Activations