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

    Neuronpedia

    INDEX
    Explanations

    explaining purpose and function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     άλλ
    0.43
     estudios
    0.43
     আদাল
    0.42
     susah
    0.41
     рынке
    0.40
     nói
    0.40
     ασ
    0.40
     reinstall
    0.39
     mensen
    0.39
    这也
    0.38
    POSITIVE LOGITS
     how
    0.74
    如何
    0.71
     behavior
    0.62
    how
    0.61
     characteristics
    0.61
     كيفية
    0.60
    如何在
    0.56
     information
    0.55
     details
    0.55
     cómo
    0.54
    Act Density 0.174%

    No Known Activations