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

    Neuronpedia

    INDEX
    Explanations

    common question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     haberse
    0.42
     যেন
    0.42
     meilleures
    0.42
    決して
    0.42
     ছাড়াই
    0.42
    যেন
    0.40
     এক
    0.38
    ᾗ
    0.38
    結果
    0.38
     migliore
    0.38
    POSITIVE LOGITS
     questions
    0.79
     často
    0.73
     Fragen
    0.71
     pertanyaan
    0.70
     Questions
    0.68
     otáz
    0.66
     question
    0.66
     vragen
    0.65
    questions
    0.63
     FAQ
    0.61
    Act Density 0.001%

    No Known Activations