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

    Neuronpedia

    INDEX
    Explanations

    asking and answering questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bood
    0.39
    แข็ง
    0.38
     دکھ
    0.38
     sıv
    0.38
    ϭ
    0.37
     lessons
    0.37
    orys
    0.37
    ˆ‚
    0.36
     сказать
    0.36
    说到
    0.36
    POSITIVE LOGITS
     posed
    1.34
     asked
    1.25
    Asked
    1.14
    asked
    1.14
     पूछा
    1.12
     पूछ
    1.05
     Asked
    1.05
     پوچھا
    1.04
    posed
    1.02
     answered
    1.02
    Act Density 0.106%

    No Known Activations