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

    Neuronpedia

    INDEX
    Explanations

    robust systems and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ti
    0.46
     Linen
    0.45
     అక్కడ
    0.44
    有點
    0.42
     Zealand
    0.42
    ohm
    0.41
     nörd
    0.41
    ເລັກ
    0.40
     ప్రకట
    0.40
     Dự
    0.40
    POSITIVE LOGITS
     annoyance
    0.49
     ঘুমের
    0.48
     अमाउंट
    0.48
     paus
    0.48
     życia
    0.48
     массив
    0.46
     chaussures
    0.46
    GPIOA
    0.44
    ക്ഷണ
    0.43
     compris
    0.43
    Act Density 0.000%

    No Known Activations