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

    Neuronpedia

    INDEX
    Explanations

    depending on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ים
    0.68
    이니까
    0.64
    ς
    0.63
    ्स
    0.62
     vacated
    0.62
     ώστε
    0.62
    그런
    0.61
     lack
    0.61
     dissimilar
    0.61
    s
    0.61
    POSITIVE LOGITS
    ent
    0.86
    ين
    0.80
    ↵
    0.75
     Notable
    0.70
    ال
    0.67
    ită
    0.66
     какая
    0.66
    િ
    0.66
    entas
    0.64
     esetben
    0.64
    Act Density 0.003%

    No Known Activations