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

    Neuronpedia

    INDEX
    Explanations

    reach out for help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     если
    0.50
     nếu
    0.47
     eğer
    0.47
    यदि
    0.46
     ако
    0.46
     หาก
    0.46
     यदि
    0.45
     pokud
    0.45
     अगर
    0.45
     اگر
    0.45
    POSITIVE LOGITS
     following
    0.57
     folgender
    0.54
     folgenden
    0.53
     one
    0.51
     следующих
    0.50
     följande
    0.49
     одном
    0.48
     следующие
    0.47
    following
    0.46
     seguintes
    0.46
    Act Density 0.010%

    No Known Activations