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

    Neuronpedia

    INDEX
    Explanations

    overall results and conclusions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    僳
    0.47
    帮你
    0.46
     eenvoudig
    0.45
     právě
    0.45
    कायदा
    0.44
     کیونکہ
    0.44
    还在
    0.44
     tiež
    0.44
    ócz
    0.44
     Ayrıca
    0.44
    POSITIVE LOGITS
    結論
    0.75
     results
    0.68
     conclusion
    0.63
     generally
    0.63
     overall
    0.62
    結果
    0.62
    results
    0.61
     resultados
    0.59
    conclusion
    0.58
     resulted
    0.57
    Act Density 0.298%

    No Known Activations