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

    Neuronpedia

    INDEX
    Explanations

    marketing and commerce terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ادى
    0.39
     presid
    0.38
    伟大
    0.38
     presidency
    0.38
     ит
    0.37
     clube
    0.37
    вели
    0.37
    orsche
    0.36
    racial
    0.36
    lois
    0.36
    POSITIVE LOGITS
     completion
    0.39
    %">
    0.38
    चं
    0.37
     konse
    0.37
     যাওয়া
    0.36
    HintPath
    0.36
     Sep
    0.36
    )?
    0.36
     mn
    0.35
    ೊಳಗ
    0.35
    Act Density 0.001%

    No Known Activations