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

    Neuronpedia

    INDEX
    Explanations

    think about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     are
    0.42
     هستند
    0.40
    ،
    0.39
     त्यांना
    0.38
    I
    0.37
     glimpses
    0.35
     मान्यता
    0.35
     appendices
    0.35
    िंग
    0.33
     Despite
    0.33
    POSITIVE LOGITS
     düşün
    0.56
     düşünü
    0.56
     THINK
    0.56
    дума
    0.55
     pensar
    0.54
    คิด
    0.53
     nghĩ
    0.52
    想想
    0.51
     pensando
    0.50
     চিন্তা
    0.50
    Act Density 0.197%

    No Known Activations