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

    Neuronpedia

    INDEX
    Explanations

    stating upfront or briefly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Analyse
    0.50
    analy
    0.45
     analyse
    0.43
     pembahasan
    0.43
     analysed
    0.42
     discusión
    0.41
     daleko
    0.41
     analiz
    0.40
    analyse
    0.40
     analý
    0.40
    POSITIVE LOGITS
     briefly
    0.91
     Briefly
    0.68
     brief
    0.64
     breve
    0.60
    brief
    0.55
     because
    0.52
    因為
    0.50
    既然
    0.50
    Brief
    0.50
     کیونکہ
    0.49
    Act Density 0.006%

    No Known Activations