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

    Neuronpedia

    INDEX
    Explanations

    asking for more information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     보세요
    0.41
     बखूबी
    0.38
    ですよ
    0.37
    निटी
    0.36
     बेशक
    0.36
    Remember
    0.35
    ាតុ
    0.35
    וט
    0.35
     বটে
    0.35
    ږي
    0.35
    POSITIVE LOGITS
     Could
    2.03
    Could
    1.91
     could
    1.72
    could
    1.64
     Would
    1.55
    Would
    1.48
     Can
    1.27
    Can
    1.26
     poderia
    1.26
     COULD
    1.25
    Act Density 0.152%

    No Known Activations