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

    Neuronpedia

    INDEX
    Explanations

    writing to express interest as advertised

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chassis
    0.43
    ogén
    0.41
     skillset
    0.41
     చా
    0.40
     அடு
    0.40
     vai
    0.39
    jectories
    0.38
     micron
    0.37
     তারপরে
    0.37
     supergiants
    0.37
    POSITIVE LOGITS
     REPLY
    0.52
     Criticism
    0.51
     editorials
    0.51
     advertisement
    0.50
     comentario
    0.50
     প্রতিবাদ
    0.49
    我想
    0.49
     articolo
    0.48
     iklan
    0.47
     misguided
    0.47
    Act Density 0.024%

    No Known Activations