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

    Neuronpedia

    INDEX
    Explanations

    configuration and setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    他
    0.47
    રી
    0.46
    Yellow
    0.46
     Crosby
    0.45
    資本
    0.42
    認証
    0.42
    Наша
    0.42
    法
    0.42
    рок
    0.42
    َف
    0.42
    POSITIVE LOGITS
    ഫോ
    0.46
     воору
    0.46
     ຫຼື
    0.46
    uacute
    0.46
     पेयजल
    0.46
    ມ
    0.46
     Eğitim
    0.45
     Intelig
    0.44
     aerodynamic
    0.44
    abhavena
    0.44
    Act Density 0.000%

    No Known Activations