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

    Neuronpedia

    INDEX
    Explanations

    specific aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     else
    0.81
     потому
    0.74
     either
    0.73
    if
    0.70
     because
    0.70
    astrophe
    0.68
    because
    0.67
       
    0.67
    ResumeLayout
    0.65
    ﴿
    0.65
    POSITIVE LOGITS
    重視
    0.77
     belangrijk
    0.76
     Zugang
    0.72
    상품
    0.68
     นัก
    0.68
     Wirtschafts
    0.67
    ្ត
    0.67
     hvordan
    0.67
     نظام
    0.65
     käyttö
    0.65
    Act Density 0.160%

    No Known Activations