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

    Neuronpedia

    INDEX
    Explanations

    geographic locations and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    formatics
    0.48
     jong
    0.47
     adicionales
    0.45
    ಿಯು
    0.45
    തര
    0.42
     instancias
    0.42
     atac
    0.42
     recruits
    0.42
     Inglis
    0.42
     fiscal
    0.40
    POSITIVE LOGITS
    {$\
    0.52
     життя
    0.47
    ！）
    0.46
    $\
    0.45
    ⵎ
    0.45
    자가
    0.44
    é
    0.44
     الري
    0.44
    ப்படும்
    0.44
     रिवर्स
    0.44
    Act Density 0.000%

    No Known Activations