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

    Neuronpedia

    INDEX
    Explanations

    consumer price index, confidence, spending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sche
    1.11
    nese
    1.08
    ding
    0.95
    şi
    0.93
    ড্ড
    0.92
    ка
    0.91
    sne
    0.91
     inertial
    0.91
    𝘩
    0.90
    dens
    0.89
    POSITIVE LOGITS
     lemak
    1.29
     nailed
    1.28
     چون
    1.26
    adays
    1.22
    ificent
    1.22
     صعب
    1.21
     ileri
    1.20
    मुळे
    1.15
     Arac
    1.15
    ภัย
    1.14
    Act Density 0.002%

    No Known Activations