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

    Neuronpedia

    INDEX
    Explanations

    key players and woman

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lymp
    0.43
    indice
    0.41
    bing
    0.39
     прошу
    0.39
    索引
    0.38
    Departamento
    0.38
     konuştu
    0.37
     тор
    0.35
    श्री
    0.35
     দপ্তর
    0.35
    POSITIVE LOGITS
     Default
    0.44
     aap
    0.43
    ጠት
    0.42
     default
    0.41
     🙂
    0.40
    👇
    0.39
     Defects
    0.39
     Socialism
    0.38
     Aap
    0.38
     Remains
    0.38
    Act Density 0.000%

    No Known Activations