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

    Neuronpedia

    INDEX
    Explanations

    numbers and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.49
    u
    0.48
    การ
    0.46
    <unused321>
    0.46
    м
    0.44
    <unused996>
    0.44
    <unused1921>
    0.44
    <unused375>
    0.44
    বদ্ধ
    0.42
    ła
    0.42
    POSITIVE LOGITS
     is
    0.41
    Σ
    0.41
    د
    0.39
     (
    0.38
    0.37
        
    0.36
    За
    0.35
    נ
    0.35
    Л
    0.35
    spring
    0.33
    Act Density 0.391%

    No Known Activations