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

    Neuronpedia

    INDEX
    Explanations

    best or leader

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nice
    0.38
    素敵な
    0.38
     可愛い
    0.38
     interesantes
    0.37
    0.37
    quả
    0.36
     प्यारी
    0.36
     lovely
    0.36
     મદ
    0.35
     遅く
    0.35
    POSITIVE LOGITS
     superior
    1.57
    superior
    1.41
     unrival
    1.39
    Superior
    1.31
     unrivalled
    1.31
     unsurpassed
    1.30
     unmatched
    1.28
     superiore
    1.28
     Superior
    1.27
     superiores
    1.23
    Act Density 0.125%

    No Known Activations