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

    Neuronpedia

    INDEX
    Explanations

    word beginnings followed by 'en' endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Extending
    0.43
    ्राष्ट
    0.43
     ा
    0.40
     इको
    0.40
    ictwa
    0.38
    闕
    0.38
    ाइयों
    0.36
     Eras
    0.36
    রাং
    0.36
     للان
    0.36
    POSITIVE LOGITS
    EN
    1.79
    en
    1.73
    ен
    1.70
    ens
    1.63
    েন
    1.60
    én
    1.52
    eni
    1.46
    enn
    1.45
    εν
    1.43
    ЕН
    1.41
    Act Density 0.055%

    No Known Activations