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

    Neuronpedia

    INDEX
    Explanations

    Acknowledgments, gratitude, thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elegir
    0.52
     combos
    0.50
     diventa
    0.50
     deviennent
    0.48
     выбира
    0.46
     choisir
    0.45
     trending
    0.45
     edgy
    0.44
    を選ぶ
    0.44
     headlines
    0.44
    POSITIVE LOGITS
     manuscript
    0.89
     Acknowledg
    0.87
     gratefully
    0.84
    Acknowledgments
    0.83
     Manuscript
    0.82
     authors
    0.78
     thanked
    0.78
     acknowled
    0.77
     acknowledges
    0.76
    感谢
    0.75
    Act Density 0.006%

    No Known Activations