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

    Neuronpedia

    INDEX
    Explanations

    list items or instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    popupIsOpen
    0.43
    >";
    0.40
    ◙
    0.39
    وفة
    0.39
    estine
    0.38
    ట్‌
    0.37
    عدة
    0.37
    ZERO
    0.37
     található
    0.37
    ່ມ
    0.37
    POSITIVE LOGITS
    martin
    0.41
     OCD
    0.38
     Pani
    0.37
    增速
    0.36
     Martin
    0.35
     Crypto
    0.34
     Paula
    0.34
     Python
    0.34
     SISO
    0.34
     Panic
    0.34
    Act Density 0.000%

    No Known Activations