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

    Neuronpedia

    INDEX
    Explanations

    contrasts and complexity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     അഭ
    0.52
    墂
    0.48
    নমেন্ট
    0.48
     ชาว
    0.48
     regenv
    0.47
     值
    0.46
     voltou
    0.46
    <unused520>
    0.45
    <unused1752>
    0.45
     ži
    0.44
    POSITIVE LOGITS
    다
    0.57
    ac
    0.51
    im
    0.50
     (
    0.50
    ult
    0.50
    2
    0.48
    af
    0.48
    .
    0.48
     potentially
    0.46
    웅
    0.46
    Act Density 0.002%

    No Known Activations