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

    Neuronpedia

    INDEX
    Explanations

    assurance or warranty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    साब
    0.50
     Upcoming
    0.39
     Bootstrap
    0.39
    坳
    0.39
    瞋
    0.38
    திர
    0.38
     mauvais
    0.38
     ആരോ
    0.38
    ঘ
    0.38
    gene
    0.37
    POSITIVE LOGITS
     власти
    0.43
    excellent
    0.41
     assurances
    0.38
     держа
    0.37
    Excellent
    0.37
     prevail
    0.36
     warranty
    0.36
     assurent
    0.36
    に近い
    0.36
     warranties
    0.35
    Act Density 0.000%

    No Known Activations