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

    Neuronpedia

    INDEX
    Explanations

    decoding signals and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elusive
    0.38
     Powerful
    0.38
    Powerful
    0.38
     quiet
    0.38
     forgotten
    0.38
     powerful
    0.37
     সেনাবাহিনীকে
    0.36
     unintentionally
    0.35
    \!
    0.35
    了一种
    0.35
    POSITIVE LOGITS
     advice
    0.42
     гене
    0.42
     decisão
    0.40
     développe
    0.38
     அறிவு
    0.38
     次
    0.38
     bior
    0.38
     разви
    0.38
    encie
    0.38
     Montessori
    0.38
    Act Density 0.001%

    No Known Activations