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

    Neuronpedia

    INDEX
    Explanations

    legal wills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    0.57
    тод
    0.55
     ingestion
    0.53
     Aldi
    0.53
     café
    0.51
    рель
    0.51
    o
    0.50
    νε
    0.50
    nics
    0.49
     degeneration
    0.48
    POSITIVE LOGITS
    కు
    0.61
     is
    0.57
     กลับ
    0.54
     drugih
    0.54
    ことが
    0.54
    arrison
    0.54
     деталей
    0.53
     ש
    0.52
    {
    0.52
     rubbed
    0.52
    Act Density 0.000%

    No Known Activations