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

    Neuronpedia

    INDEX
    Explanations

    slow and interesting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    образ
    0.43
    ப்படுத்தும்
    0.42
    으로써
    0.41
     vocabulary
    0.40
     keempat
    0.40
     ketiga
    0.40
     bazaar
    0.37
     princesses
    0.37
    ானது
    0.37
    ǚ
    0.37
    POSITIVE LOGITS
    久的
    0.39
     slow
    0.39
     slowdown
    0.39
    速率
    0.39
    Slow
    0.38
    緩
    0.38
     stret
    0.37
    Interesting
    0.36
    slow
    0.36
     slowed
    0.36
    Act Density 0.002%

    No Known Activations