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

    Neuronpedia

    INDEX
    Explanations

    list separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onions
    0.42
     hallucin
    0.41
     inferred
    0.40
    ابہ
    0.39
     electrolytes
    0.39
    انة
    0.39
     collided
    0.38
     cockroaches
    0.38
     milliliters
    0.38
     repeatability
    0.38
    POSITIVE LOGITS
    <h2>
    0.53
    これらの
    0.39
    ```
    0.38
    alami
    0.38
    <h6>
    0.36
    笔记
    0.36
    <h3>
    0.35
    Document
    0.35
    <h1>
    0.34
    <h4>
    0.33
    Act Density 0.000%

    No Known Activations