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

    Neuronpedia

    INDEX
    Explanations

    code sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Nasdaq
    0.44
     reyes
    0.42
     palabras
    0.42
     escritores
    0.42
     piped
    0.41
    Just
    0.41
     लावा
    0.40
    狱
    0.39
     raises
    0.39
     ede
    0.39
    POSITIVE LOGITS
     Sections
    0.36
    尤
    0.35
     comp
    0.35
     antibody
    0.35
    <unused14>
    0.33
    лик
    0.33
     SIT
    0.33
     শী
    0.33
    сад
    0.32
     agitated
    0.32
    Act Density 0.001%

    No Known Activations