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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gazette
    0.59
     Coverage
    0.57
     മിക
    0.57
     멀
    0.56
     Among
    0.56
     Achieve
    0.55
     Alej
    0.54
    igual
    0.54
    বস্ত
    0.54
     severally
    0.54
    POSITIVE LOGITS
    痔
    0.66
    訣
    0.57
     relais
    0.56
    াড়াও
    0.55
    廣告
    0.54
    daw
    0.54
    妙
    0.53
    的模型
    0.53
     underground
    0.52
     propeller
    0.52
    Act Density 0.000%

    No Known Activations