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

    Neuronpedia

    INDEX
    Explanations

    countries and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     algoritmo
    0.39
    手册
    0.37
     atoms
    0.35
     degrés
    0.35
     appliquée
    0.34
     maximale
    0.33
     luciferase
    0.33
     চাপের
    0.33
     হ্যান
    0.33
    魈
    0.33
    POSITIVE LOGITS
     Indonesia
    0.50
     southwest
    0.50
     northeast
    0.50
     southwestern
    0.49
     ประเทศ
    0.48
     Italy
    0.48
     west
    0.47
    Indonesia
    0.47
     southeastern
    0.46
     northwestern
    0.46
    Act Density 0.053%

    No Known Activations