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

    Neuronpedia

    INDEX
    Explanations

    list item markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olen
    0.52
    v
    0.51
    u
    0.50
     slice
    0.49
    uc
    0.48
    </b>
    0.47
    ole
    0.44
    yla
    0.44
    ushan
    0.44
    </strong>
    0.44
    POSITIVE LOGITS
     максимально
    0.59
    等級
    0.54
     genoeg
    0.53
    觀察
    0.50
    風格
    0.49
     maximale
    0.49
     entièrement
    0.49
     Noyes
    0.48
     Ajoutez
    0.48
     একেবারে
    0.48
    Act Density 0.000%

    No Known Activations