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

    Neuronpedia

    INDEX
    Explanations

    affirmation and auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Unless
    0.40
     Essentially
    0.36
    Unless
    0.36
     절대
    0.35
    するのが
    0.35
    Dane
    0.34
    絶対
    0.34
    чної
    0.33
    ๊ก
    0.33
     сло
    0.33
    POSITIVE LOGITS
    确实
    1.67
     DOES
    1.66
     DID
    1.57
     does
    1.55
    確實
    1.52
    does
    1.42
     do
    1.39
     did
    1.38
     DO
    1.32
     memang
    1.28
    Act Density 0.192%

    No Known Activations