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

    Neuronpedia

    INDEX
    Explanations

    dark, ware, protection, may, to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دوره
    0.43
     اتفاق
    0.41
     pon
    0.40
     Medicine
    0.38
    move
    0.37
     set
    0.37
     dansk
    0.37
     forms
    0.36
     عند
    0.36
     emerge
    0.35
    POSITIVE LOGITS
    மஹ
    0.44
    ंकि
    0.42
     эмоциона
    0.41
    жити
    0.41
    綺麗な
    0.40
    வ்வாற
    0.39
     Jaaye
    0.38
    illah
    0.38
     वाहन
    0.38
    шру
    0.37
    Act Density 0.008%

    No Known Activations