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

    Neuronpedia

    INDEX
    Explanations

    English language learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     brisket
    0.51
     equity
    0.51
     mulch
    0.51
     homeowner
    0.50
     odometer
    0.50
     horsepower
    0.49
     estoppel
    0.48
     pru
    0.47
     eviction
    0.47
     arcane
    0.46
    POSITIVE LOGITS
     Language
    1.09
    Language
    1.07
    英语
    1.07
     English
    1.05
    language
    1.01
    英語
    1.01
    English
    0.99
     اللغة
    0.98
     영어
    0.96
     زبان
    0.95
    Act Density 0.204%

    No Known Activations