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

    Neuronpedia

    INDEX
    Explanations

    seals and sealing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Yaad
    1.06
     aspett
    0.99
    <u>
    0.92
    postfix
    0.92
     yani
    0.91
    Ngoài
    0.90
    Chicken
    0.87
     kapan
    0.87
     Bcl
    0.87
    llvm
    0.87
    POSITIVE LOGITS
    ب
    1.33
     ponctués
    1.28
    ྛ
    1.18
    鲟
    1.17
     sulfonic
    1.14
    ுக்கு
    1.13
    רות
    1.12
    𝑛
    1.10
    logged
    1.09
    ंध्र
    1.08
    Act Density 0.023%

    No Known Activations