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

    Neuronpedia

    INDEX
    Explanations

    everyone [verb]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    都不会
    1.21
     नाहीत
    1.06
     nisu
    1.05
    都不是
    1.03
    都沒有
    0.96
    都不
    0.90
    స్తాయి
    0.89
    都可以
    0.88
     mogą
    0.87
     eivät
    0.87
    POSITIVE LOGITS
     seems
    1.19
     knows
    1.17
     has
    1.17
     was
    1.15
     gets
    1.15
     keeps
    1.07
     tends
    1.07
     is
    1.05
     goes
    1.01
     expects
    1.00
    Act Density 0.005%

    No Known Activations