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

    Neuronpedia

    INDEX
    Explanations

    articles preceding nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     benefitted
    0.53
     amongst
    0.50
     topped
    0.47
     iedere
    0.47
     unsurprisingly
    0.47
    neath
    0.46
     attempting
    0.46
     those
    0.45
     deced
    0.44
     Ну
    0.44
    POSITIVE LOGITS
     XNUMX
    0.78
     rapproche
    0.61
     interloc
    0.54
     analyzes
    0.52
    NUMX
    0.52
     ​​
    0.51
     prerog
    0.51
     peculiarity
    0.50
     hegemony
    0.46
     և
    0.46
    Act Density 0.007%

    No Known Activations