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

    Neuronpedia

    INDEX
    Explanations

    washing process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    전
    0.57
     Traffic
    0.54
    الط
    0.51
    ท
    0.51
    좋
    0.49
    ፈር
    0.48
    ดี
    0.48
    ോട്ട്
    0.48
     ट्रैफिक
    0.47
    자
    0.47
    POSITIVE LOGITS
    ,”
    0.46
    abyte
    0.46
    ,(
    0.42
     wary
    0.42
     enthalpy
    0.42
     entice
    0.42
     zusätzlich
    0.42
     untrained
    0.42
     suhu
    0.41
     tabindex
    0.41
    Act Density 0.001%

    No Known Activations