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

    Neuronpedia

    INDEX
    Explanations

    human or humans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ارتی
    0.65
     সিদ্দিক
    0.60
    राबाद
    0.60
    व्स
    0.59
     અર
    0.59
    कोट
    0.58
    adocia
    0.58
    ငယ်
    0.58
    ｀
    0.58
    ້ອ
    0.57
    POSITIVE LOGITS
     human
    5.41
     humans
    4.94
    Human
    4.88
    human
    4.87
     Human
    4.83
     Humans
    4.54
    Humans
    4.47
    humans
    4.34
     HUMAN
    4.32
     humano
    4.30
    Act Density 0.742%

    No Known Activations