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

    Neuronpedia

    INDEX
    Explanations

    Okay, let's break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    奇怪
    0.49
     immor
    0.45
    يمق
    0.41
    Ꮁ
    0.40
     নিষেধ
    0.40
    sterdam
    0.40
    вичай
    0.40
    ޏ
    0.40
     বিস্ম
    0.39
     বিশ্বাস
    0.39
    POSITIVE LOGITS
     plethora
    0.59
     довольно
    0.58
     prolific
    0.53
    꽤
    0.51
     достаточно
    0.50
     plenty
    0.50
     khá
    0.47
     hefty
    0.47
     కీలక
    0.47
     varied
    0.46
    Act Density 0.126%

    No Known Activations