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

    Neuronpedia

    INDEX
    Explanations

    historical, scientific, or narrative contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    瀚
    0.41
    خ
    0.39
    》。
    0.38
     لاست
    0.38
     largement
    0.38
    R
    0.36
    เท่า
    0.36
     يه
    0.36
    べ
    0.36
    مه
    0.35
    POSITIVE LOGITS
     acted
    0.53
     memiliki
    0.48
     spends
    0.47
     বেড়ে
    0.45
     λοι
    0.45
     обладает
    0.45
     lived
    0.44
    şı
    0.44
     awoke
    0.43
    可以说是
    0.43
    Act Density 0.007%

    No Known Activations