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

    Neuronpedia

    INDEX
    Explanations

    explaining with imagine you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نشوف
    0.52
    ۔
    0.49
    ly
    0.46
     поро
    0.46
    isOn
    0.45
    ī
    0.43
    ╮
    0.43
    strcpy
    0.43
    ஶ
    0.43
     он
    0.42
    POSITIVE LOGITS
     Toute
    0.48
     Selenium
    0.43
     smartest
    0.43
     갑
    0.43
    arnas
    0.43
    عهد
    0.42
     진
    0.41
     ততদিন
    0.41
     Cliquez
    0.40
     früheren
    0.40
    Act Density 0.016%

    No Known Activations