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

    Neuronpedia

    INDEX
    Explanations

    strength and focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Aenean
    0.45
    Whatsapp
    0.40
     آگے
    0.39
     maksud
    0.38
     മൃ
    0.38
    agam
    0.38
    getTotal
    0.38
    洙
    0.38
     border
    0.38
     Border
    0.38
    POSITIVE LOGITS
     migrating
    0.39
     placed
    0.38
     καθ
    0.38
     wood
    0.37
     contained
    0.35
     Seitz
    0.35
     טוב
    0.34
    ENDOR
    0.34
    embrance
    0.34
    )}"
    0.34
    Act Density 0.001%

    No Known Activations