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

    Neuronpedia

    INDEX
    Explanations

    words starting with W

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     widening
    1.28
    옵
    1.22
     tota
    1.21
    使
    1.19
    wedding
    1.18
     reigning
    1.15
     вы
    1.13
     вопло
    1.13
     Zebra
    1.12
     Миха
    1.12
    POSITIVE LOGITS
    nesday
    2.23
    consin
    1.79
     Wednesdays
    1.70
    ্ল্ড
    1.68
     Warriors
    1.53
    णिज्य
    1.44
    NESDAY
    1.41
     deeds
    1.40
    ands
    1.39
    বসাই
    1.38
    Act Density 0.663%

    No Known Activations