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

    Neuronpedia

    INDEX
    Explanations

    lottery or politics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UTRON
    0.53
     рэгістра
    0.52
     аўтаматы
    0.51
     гульнявыя
    0.50
    뮐
    0.50
     Еўро
    0.49
    毕业生
    0.49
     нацыяна
    0.48
    EndZ
    0.48
     dentées
    0.47
    POSITIVE LOGITS
    0.63
     t
    0.57
     yang
    0.57
     T
    0.56
      
    0.56
     Mimpi
    0.55
     y
    0.53
    ↵
    0.52
     the
    0.51
     togel
    0.51
    Act Density 0.000%

    No Known Activations