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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ২৯
    0.39
     ۱۹
    0.39
    ৪৩
    0.37
     ৫৮
    0.37
    ২৬
    0.36
     ۹
    0.36
    ৩৪
    0.36
     essentially
    0.35
    ২৮
    0.34
     १६
    0.34
    POSITIVE LOGITS
    5
    0.60
    <unused883>
    0.47
    0
    0.46
    3
    0.45
    4
    0.42
    2
    0.41
    7
    0.41
    1
    0.39
    ️⃣
    0.38
    е
    0.38
    Act Density 0.967%

    No Known Activations