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

    Neuronpedia

    INDEX
    Explanations

    truth and reality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لها
    0.69
    ტის
    0.65
    쐞
    0.60
    드를
    0.59
    entions
    0.56
    gota
    0.56
    போது
    0.55
    رخ
    0.55
    لنا
    0.55
    im
    0.54
    POSITIVE LOGITS
     truth
    0.97
     truths
    0.90
     সত্য
    0.87
    真相
    0.79
    на
    0.77
     Wahrheit
    0.74
     Truth
    0.73
    Truth
    0.73
     حقیقت
    0.71
     realities
    0.68
    Act Density 0.047%

    No Known Activations